Design Reliable Agent Tools
Ambiguous tools cause routing errors, malformed calls, and failed recovery. This skill provides practical patterns for clear schemas, descriptions, responses, and tool catalogs.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "tool-design" from https://skillstore.io/skills/muratcankoylan-tool-design.md and its manifest at https://skillstore.io/api/skills/muratcankoylan-tool-design/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "tool-design". Review a customer lookup tool with an unclear description and generic errors.
Expected outcome:
Using "tool-design". Audit search_orders and find_orders in the same catalog.
Expected outcome:
The tools have overlapping activation scenarios. Merge them or define distinct data sources, filters, return shapes, and selection rules.
Using "tool-design". Assess a catalog with inconsistent customer identifiers.
Expected outcome:
Standardize on customer_id across tool names, parameters, examples, responses, and errors. Add compatibility handling before removing older identifiers.
All 49 static findings are false positives from documentation markup, ordinary prose, or sandboxed command examples. The Python utility performs no network or process execution.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/muratcankoylan-tool-design/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/muratcankoylan-tool-design?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/muratcankoylan-tool-design?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/muratcankoylan-tool-design/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/muratcankoylan-tool-design.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>muratcankoylan. (2026). tool-design security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/muratcankoylan-tool-design/audits/8@techreport{muratcankoylan-muratcankoylan-tool-design-2026,
author = {muratcankoylan},
title = {tool-design security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/muratcankoylan-tool-design/audits/8},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "tool-design security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
- name: "muratcankoylan"
date-released: "2026-08-09"
url: "https://skillstore.io/skills/muratcankoylan-tool-design/audits/8"
identifiers:
- type: other
value: "skillstore:muratcankoylan-tool-design:audit:8"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
asmayaseen-tool-design
2026-08-21
muratcankoylan-tool-design
2026-08-21
chakshugautam-tool-design
2026-08-21
sickn33-tool-design
2026-08-21
Create a complete description, schema, response shape, and recovery contract before implementation.
Identify overlapping purposes, naming collisions, inconsistent parameters, and unclear selection guidance.
Use observed failures to clarify descriptions, constraints, examples, and retry guidance.
Rewrite this tool description. State what it does, when to use it, accepted inputs, returned data, and recoverable errors: {description}Design an agent tool for {workflow}. Include a verb-noun name, typed parameters, defaults, response formats, examples, errors, and retry guidance.Audit these tools for overlapping activation scenarios, inconsistent names, schema conflicts, namespace collisions, missing errors, and oversized responses: {catalog}Compare specialized tools with a sandboxed primitive-tool design for {system}. Assess safety boundaries, routing accuracy, token cost, maintenance, and evaluation criteria.Author
muratcankoylanLicense
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Repository
https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/skills/tool-designRef
02be9409c79ca1183f7844009c14d9df684d0cf9
Maintenance freshness
8/11/2026
Usage
13 downloads · 229 views
File structure
Compress Long Agent Contexts Reliably
Long agent sessions can lose decisions, file history, and next steps during compression. This skill provides structured methods and probes that preserve operational context.
Build Reliable Agent Evaluations
Agent quality is difficult to measure because outputs vary and may have several valid forms. This skill builds repeatable rubrics, tests, gates, and monitoring.
Diagnose and Repair Context Degradation
Long contexts can hide critical instructions, preserve bad claims, and mix conflicting tasks. This skill diagnoses the failure pattern and recommends placement, filtering, compression, isolation, or recovery strategies.
Optimize AI Context for Cost and Quality
Long AI sessions waste tokens and lose important context. This skill provides measured strategies for budgeting, masking, compaction, caching, retrieval, and partitioning.
Design Reliable Multi-Agent Systems
Multi-agent designs often add cost and coordination failures without improving outcomes. This skill helps select topologies, handoffs, consensus methods, and recovery controls.
Build Reliable LLM Evaluation Systems
LLM quality reviews often drift because judges use vague criteria and exhibit systematic bias. This skill provides calibrated rubrics, comparison methods, and validation metrics.
Build Claude Code Plugin Structure
by anthropics
Plugin authors need consistent layouts that Claude Code can discover. This skill explains manifests, components, hooks, MCP servers, and portable paths for reliable plugins.
Avoid Drizzle ORM Migration Pitfalls
by BarisSozen
Drizzle ORM schema mistakes can break migrations and weaken type safety. This skill guides Claude, Codex, and Claude Code toward safer patterns.
Build MCP Servers for AI Integrations
by Doyajin174
Connecting AI assistants to services requires careful server design. This skill guides planning, TypeScript structure, tool annotations, testing, and evaluation for MCP servers.
Build Production-Ready MCP Servers
by sickn33
Building MCP servers requires protocol, SDK, and evaluation choices that are easy to miss. This skill guides planning, implementation, testing, and Microsoft ecosystem decisions for reliable integrations.
Add Malli Schemas to Metabase API Endpoints
by metabase
Metabase endpoints can fail when request and response schemas do not match runtime data. This skill guides accurate Malli schemas using established project patterns.
Design Reliable Backend Models
by EIS-ITS
Database models often drift without clear naming, relationships, and constraints. This skill guides Claude, Codex, and Claude Code through consistent ORM model design.