List External RFIs

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

The description adds useful behavioral context beyond annotations: read-only assertion, defaulting of company_id and project_id from procore_set_config, and common HTTP error statuses. However, it also states 'Returns a single JSON object,' which is likely inaccurate for a list endpoint and misrepresents the response shape. Since the description partially contradicts its own stated behavior and the endpoint's nature, transparency is only average.

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 moderately concise and includes a mix of useful metadata (error handling, defaults, API path). However, the contradictory 'single JSON object' sentence is both redundant and misleading, and the 'Required parameters' line repeats schema information. Overall it earns a middle score.

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 14-parameter list tool with no output schema, the description should clarify the return shape (array of external RFIs) and pagination behavior. Instead it incorrectly says 'Returns a single JSON object.' It covers read-only and error handling well, but the critical list-versus-single distinction is missing. The description is incomplete and potentially misleading in a key area.

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 baseline is 3. The description adds value only for company_id and project_id by explaining their default behavior when omitted, which is not in the schema. Other parameters are left to the schema or the external filtering link, so no additional meaning is provided for them.

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 action (returns all External RFIs) and scope (specified Project), but the later claim 'Returns a single JSON object describing the external RFI' conflicts with the list semantics and the endpoint. This muddies whether the tool returns a collection or a single record, so the purpose is not entirely clear.

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 only usage guidance is 'Use this when you already know which external RFI you want and need its full field set,' which paradoxically describes a lookup of a single known RFI, more aligned with show_external_rfi. There is no guidance on when to prefer alternatives, when not to use it, or how filtering fits relative to other list variants. This could lead an agent to call this tool when show_external_rfi is intended.

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