List Submittals (Deprecated)

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

The description goes well beyond the annotations by detailing pagination behavior (page and per_page, response reports pages remaining), error payload structure with common HTTP status codes (401, 403, 404), and the risk of removal due to deprecation. This gives the agent a clear picture of what to expect and how to handle failures, adding significant value beyond the readOnlyHint 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 a single dense paragraph with useful information, but it contains redundancy (deprecation stated twice) and trailing metadata (API category and endpoint path) that may not be essential. It front-loads the deprecation warning and alternative, which is good, but the overall structure could be tightened.

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 has 21 parameters and no output schema, the description covers important operational details: return format, pagination, error handling, and required parameters. It lacks a description of the submittal object structure, but for a list tool the JSON array description is reasonably sufficient. The link to filtering docs also helps contextualize the many filter parameters.

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 provides descriptions for all 21 parameters, so schema coverage is 100%. The description only reiterates that project_id is required and mentions page/per_page for pagination, which is already in the schema. The link to filtering documentation is helpful but does not add new semantic detail for individual parameters, so it stays at the baseline.

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 this tool lists submittals and returns a JSON array, with the primary use case of discovering submittals or looking up an ID. It explicitly labels the endpoint as deprecated, but does not directly name sibling tools like 'list_submittals_on_a_project', so differentiation relies on the deprecation notice and the pointer to use procore_search_endpoints instead.

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 guidance: it explicitly says to use the /submittals endpoint instead, and tells the agent to prefer a newer version and use procore_search_endpoints to find it. It also gives a specific use case (discover submittals or look up an ID) but does not exhaustively enumerate when not to use this tool beyond the deprecation notice.

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