List Recycled Near Misses

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds valuable behavioral context beyond that: it explains the pagination behavior ('page and per_page control pagination and the response reports how many pages remain'), and details failure modes including specific HTTP statuses (401, 403, 404) and their likely causes. This goes well beyond the 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?

The description is dense but well-structured, front-loading the core purpose and adding supporting details. Every sentence contributes useful information, though the final 'Required parameters: project_id' sentence is slightly redundant since the schema already marks it required. Minor redundancy reduces the score from 5.

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?

For a 13-parameter list tool with no output schema, the description covers the return type ('JSON array'), pagination semantics, error handling with common status codes, the config default for project_id, and the endpoint path. It also mentions restoration via the restore endpoint. This is exceptionally complete for understanding the tool's behavior and response.

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 13 parameters have schema descriptions (100% coverage), but the tool description adds crucial semantics not present in the schema. It explains that incident_id scopes results to a single incident, that page/per_page control pagination, and that project_id defaults to the configured value when omitted. This significantly helps correct invocation.

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 returns a paginated list of soft-deleted near miss records from the recycle bin. It explicitly distinguishes this from the active near misses list by mentioning 'soft-deleted' and 'recycle bin', and notes it can be scoped via incident_id. This is a specific verb+resource+scope that stands apart from sibling tools like list_near_misses.

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?

The description provides a clear use case: 'Use this to discover recycled near misses or to look up the id of one before calling a tool that needs it.' It also references the restore endpoint and notes that project_id defaults to a configured value. However, it does not explicitly state when not to use it (e.g., for active records, use list_near_misses), though this is strongly implied.

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