List Recycled Injuries

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

Beyond the readOnlyHint, idempotentHint, and destructiveHint annotations, the description adds rich behavioral context: pagination controls and response format ('Returns a JSON array... response reports how many pages remain'), deprecation of keys, defaulting behavior for project_id, and concrete failure modes (401/403/404). This far exceeds what annotations alone provide.

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 with information but every sentence serves a purpose: purpose, scoping, relationship to main list, deprecation notice, usage guidance, default behavior, return format, read-only assurance, error handling, and endpoint reference. It is front-loaded with the primary action and avoids redundancy.

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?

With 17 parameters and no output schema, the description does a good job covering pagination, scoping, error payloads, and default project_id. However, it does not describe the structure of each injury record beyond mentioning deprecated keys; while it references 'as documented below,' the actual response fields are not enumerated. This leaves a small gap for an agent needing to parse results.

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 description coverage is 100%, so the schema already documents all 17 parameters. The description adds value by noting 'project_id defaults to the value set by procore_set_config when omitted,' which is a useful clarification beyond the schema's 'required' flag. It also references incident_id scoping, but this is already covered in the schema. Overall, the description complements but does not heavily supplement 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?

The description opens with a specific verb and resource: 'Returns a paginated list of soft-deleted injury records in the project's recycle bin.' It clearly distinguishes this from siblings like 'list_injuries' (main list), 'show_recycled_injury' (single retrieval), and 'retrieve_recycled_injury' (restore) by emphasizing soft-deleted scope and recycle bin location.

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 explicitly states when to use it: 'Use this to discover recycled injuries or to look up the id of one before calling a tool that needs it.' It also points to an alternative by noting 'Recycled injuries can be restored via the restore endpoint,' and references the main injuries list via 'Supports the same filtering and sorting options.'

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