List Prime Contract Attachments

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

The description adds valuable error-code context (401/403/404) and explicitly states the operation is read-only, which is consistent with annotations. Yet it contradicts itself by claiming to return a list while later saying 'Returns a single JSON object,' and it incorrectly states that required parameters can default when omitted. These inconsistencies undermine trust in the described behavior.

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 verbose and repetitive, restating required parameters and including API endpoint details that are not essential. The internal contradictions force the reader to re-interpret the text, and the structure is not front-loaded with the most critical information in a clear, digestible way.

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?

The description covers prerequisites and error handling, which is helpful, but it fails to clarify the actual return shape (list vs single object) and does not mention pagination behavior even though page and per_page are in the schema. The contradictions and missing return-type clarity are significant gaps for a list tool with no output schema.

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 the input schema fully documents all six parameters. However, the description's claim that company_id and project_id default to procore_set_config values when omitted directly contradicts the schema marking them as required. This misleading addition lowers the value beyond what the schema already provides.

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 opening sentence clearly identifies the tool as returning a list of attachments for a given prime contract, establishing a specific verb and resource. However, the subsequent phrase 'when you already know which prime contract attachment you want' incorrectly implies a show operation, creating mild ambiguity about whether this is a list or fetch-by-id tool.

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 useful prerequisite: prime_contract_id must reference an existing parent record and should be resolved using the matching list tool first. It also notes that company_id and project_id may inherit defaults from procore_set_config. However, it offers no clear guidance on when to use this tool versus alternatives, and the 'when you know which attachment you want' phrasing is confusing for a list operation.

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