search_issues

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

Describes the search scope (all repos) and available filters, but with no annotations, it lacks details on return format, pagination behavior, or any side effects. The description is adequate but does not fully compensate for the absence of annotations.

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?

Three sentences, each serving a distinct purpose: defining function, providing usage guidance and a parameter tip, and contrasting with a sibling. No wasted text.

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?

Given no output schema and 6 well-documented parameters, the description covers the core purpose, filtering options, and cross-repo scope. Lacks details on response structure but is sufficient for a search tool in a GitHub-like context.

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?

All 6 parameters have descriptions in the schema (100% coverage), so baseline is 3. The description adds a minor usage tip for the 'type' parameter but does not provide significant additional meaning beyond the schema.

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?

Clearly states the tool searches issues and pull requests across all visible repositories by keyword, type, state, and labels. Explicitly contrasts with sibling list_issues for per-repo listing, making the scope unambiguous.

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 advises when to use ('find issues about X', duplicate detection) and when not (use list_issues for a single repo). Provides a specific parameter tip: set type='issues' to exclude pull requests.

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