search_decisions

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are not provided, so description carries full burden. It implies the tool is a safe read operation (searching) with no destructive behavior stated. Strongly indicates it's a required prerequisite step, but doesn't explicitly state it's read-only.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is front-loaded with the mandatory instruction. While verbose, every sentence is meaningful. Bold and caps for emphasis make it clear. Could be slightly shorter but maintains effectiveness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers when to call, what to query, and expected outcomes. Does not describe output structure (e.g., list of decisions with details), but usage guidance is comprehensive enough for agent to act correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and description adds value beyond schema: provides examples for query parameter, and gives explicit guidance for project parameter (REQUIRED, extract from path, call list_projects if unsure).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: search for existing decisions/conventions before making code changes. It uses the verb 'search' and resource 'decisions', and distinguishes itself from siblings like add_decision, delete_decision, etc. by emphasizing it must be called first.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'MANDATORY: Call this FIRST before ANY code changes.' Provides detailed when-to-use scenarios (add feature, modify code, fix bug, etc.) and what to query. Also explains what to do if no decisions exist (proceed freely) and if they exist (follow them).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.