Procore MCP Server

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

No annotations are provided, so the description carries the full burden. It states 'Show Submittal' and includes an HTTP GET method, implying a read-only operation, but doesn't explicitly confirm safety (e.g., non-destructive), disclose authentication needs, rate limits, error conditions, or what 'show' entails (e.g., returns full details, supports pagination via 'page' and 'per_page' parameters). The description lacks behavioral details beyond the implied read action.

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 concise with two parts: a brief purpose statement and technical endpoint details. It's front-loaded with the core action ('Show Submittal'), and the additional context is minimal but relevant. However, the technical endpoint could be considered redundant if the agent already has structured API info, though it doesn't add unnecessary verbosity.

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 complexity (a read operation with 4 parameters, 2 required), no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., submittal object details), error handling, or behavioral traits like pagination behavior implied by 'page' and 'per_page'. For a tool with no structured output or annotations, more descriptive context is needed to guide the agent effectively.

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 description coverage is 100%, with clear descriptions for all parameters (e.g., 'Unique identifier for the project', 'Submittal ID', pagination details). The description adds no parameter semantics beyond what the schema provides—it doesn't explain relationships (e.g., 'id' must belong to 'project_id') or usage nuances. With high schema coverage, the baseline score of 3 is appropriate as the schema does the heavy lifting.

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 'Show Submittal' is a verb+resource phrase that indicates the tool retrieves a submittal. However, it's vague about what 'show' entails (e.g., retrieve details, view metadata) and doesn't distinguish it from sibling tools like 'show_submittal_v1_0' or 'show_submittal_v1_1', which could be different versions or implementations. The inclusion of '[Project Management/Submittals] GET /rest/v1.0/projects/{project_id}/submittals/{id}' adds technical context but doesn't clarify the functional purpose beyond the name.

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?

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites (e.g., needing a specific project or submittal ID), exclusions, or comparisons to sibling tools like 'list_submittals' or other 'show' variants. The agent must infer usage from the parameters and context alone.

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