Delete Markups

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

Beyond the destructiveHint annotation, the description adds irreversibility ('Permanently removes the markup. This cannot be undone'), idempotency behavior ('a repeat call returns 404'), and error payload details (401/403/404). It also notes defaulting of company_id and project_id, which is not in annotations. No contradiction with annotations; idempotentHint is compatible with a second call returning 404.

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 front-loads the core purpose in the first sentence and then packs necessary operational detail into each subsequent sentence: prerequisites, defaults, irreversibility, error behavior, required parameters, and API reference. No sentence is wasted, though it is longer than average.

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 delete operation with no output schema, the description covers invocation requirements (required params, defaults), prerequisites (id resolution), safety (permanence/irreversibility), error handling (status codes), and API location. The agent has enough information to correctly select and call this tool in its 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?

The input schema has descriptions for all four parameters, but they are minimal ('URL path parameter', 'JSON request body field'). The description adds meaning: company_id and project_id default to procore_set_config values, viewer_doc_id must be an existing parent record, and all four are required. However, the 'markups' array parameter is not explained in detail—what it should contain (presumably markup IDs) is left implicit. This is a gap, so baseline 3 is appropriate.

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: 'Deletes markups for a specific company, project, and document.' This clearly distinguishes it from sibling tools like modify_markups or list markups, and the scope is explicit. It is not a tautology and provides no ambiguity about the operation.

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 prerequisites: 'Confirm the target id with the matching show or list tool before calling' and 'viewer_doc_id must identify an existing parent record — resolve it with the matching list tool first.' It also explains defaulting behavior for company_id and project_id. It does not explicitly exclude alternatives like remove_an_existing_markup, but the guidance is actionable and clear.

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