Revoke A Person'S Login

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

Beyond the annotations (destructiveHint, idempotentHint), the description adds critical behavioral details: the person remains as an assignable resource, the operation is permanent and cannot be undone, a repeat call returns 404, and failure responses carry HTTP status codes (401, 403, 404). This provides context on consequences and error handling that annotations alone do not convey. No contradictions with 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 information-dense and well-structured, with clear sentences covering purpose, prerequisites, side effects, idempotency, and errors. It loses a point for minor redundancy: 'Permanently removes the person's login' and 'This cannot be undone' say the same thing, and 'Required parameters: company_id, person_id' duplicates the schema. Still, it is concise enough for the amount of context provided.

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 the tool's destructive nature and lack of an output schema, the description is remarkably complete. It explains prerequisites (resolve ids), default behavior (company_id), permanence/reversibility, idempotency (repeat 404), error handling (401/403/404), the API resource path, and endpoint. No significant gaps are apparent.

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?

The input schema already covers both parameters with descriptions (100% coverage), but the description adds practical semantics: company_id can default from procore_set_config when omitted, and person_id must reference an existing record resolved via a list tool. However, the statement about company_id being optional conflicts with the schema marking it as required, adding a slight ambiguity—though the description's guidance is still valuable.

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 with a specific verb and resource: 'Revoke a Person's login but leave them in as an assignable resource.' It also emphasizes that the login is permanently removed, which differentiates it from other person-related tools like enable_a_person_to_log_in or delete_a_person. The scope and side effect are 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?

The description provides clear context on when to use the tool by advising to confirm the target id with a matching show/list tool and to resolve person_id via the list tool first. It also explains the company_id default from procore_set_config and common error scenarios. However, it does not explicitly name alternative tools (e.g., enable_a_person_to_log_in) or state when not to use it, though the contrast with 'leave them in as assignable resource' implies the difference from full deletion.

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