List Recycled Witness Statements

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

Annotations already declare readOnly/read-only, but the description adds substantial behavioral context: pagination details ('page and per_page control pagination and the response reports how many pages remain'), error payload structure with common HTTP statuses (401/403/404), and default project_id fallback. This goes well beyond what annotations provide and discloses operational behavior important for invocation.

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 efficiently structured and front-loaded: purpose first, then usage, then pagination/behavior, then errors, then required params/API endpoint. Every sentence adds value with no filler or redundancy, despite being fairly detailed.

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, the description covers return type (JSON array) and pagination status, plus error handling and API endpoint. It does not enumerate the fields of each recycled witness statement, which might be useful, but for a list/discovery tool the provided information is sufficient to select and invoke correctly. High complexity (9 params) is well addressed.

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%, so baseline is 3. The description adds meaningful semantics beyond the schema: `project_id` defaults to `procore_set_config` value, `page`/`per_page` control pagination, and `incident_id` scopes to a specific Incident. It doesn't detail every filter, but the schema already handles those, so this is a solid enhancement.

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 it 'Returns a list of Recycled Witness Statements for a given project (or Incident, if incident_id is present)' — a specific verb, resource, and scope. It also differentiates from siblings by explicitly positioning it for discovering recycled statements and looking up IDs before calling other tools, unlike `list_witness_statements` or `show_recycled_witness_statement`.

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 gives clear use cases: 'Use this to discover recycled witness statements or to look up the id of one before calling a tool that needs it.' It implies scope via project/incident and notes default project_id behavior. While it doesn't explicitly name alternative tools to use for non-recycled statements, the context is strong enough to guide tool selection.

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