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 of behavioral disclosure. It mentions a GET endpoint, implying a read-only operation, but does not explicitly state whether it's safe, idempotent, or has side effects. It lacks details on pagination behavior (though parameters like 'page' and 'per_page' are in the schema), rate limits, authentication needs, or error handling. The description adds minimal behavioral context beyond the implied HTTP method.

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 run-on sentence that mixes the tool name, a category tag, and an API endpoint without clear structure. It is under-specified rather than concise—key details like the action verb and scope are missing. The information is not front-loaded effectively; the API endpoint is included but does not add value for an AI agent selecting tools. The description wastes space on redundant elements.

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 (5 parameters, no annotations, no output schema), the description is incomplete. It does not explain the return values, pagination behavior, or error conditions. While the schema covers parameters, the description fails to provide necessary context for a list operation, such as what the output contains (e.g., email metadata or full content) or how to handle large result sets. The lack of annotations and output schema increases the burden on the description, which it does not meet.

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 all parameters documented in the input schema (e.g., 'project_id' as 'Unique identifier for the project'). The description adds no additional parameter semantics—it only includes the API path with '{project_id}' but no explanation of the other parameters. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, though the description does not compensate for any gaps (there are none).

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 'List of Emails. [Project Management/Emails] GET /rest/v1.0/project/{project_id}/email_communications/emails' is tautological—it restates the tool name ('List of Emails') and adds an API endpoint without clarifying the action. It lacks a specific verb (e.g., 'retrieve' or 'fetch') and does not distinguish this tool from its many sibling tools (e.g., 'list_of_company_level_emails'), which is critical given the context. The description fails to specify what resource it operates on beyond the generic 'Emails'.

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 no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, context, or exclusions. Given the numerous sibling tools (e.g., 'list_of_company_level_emails', 'list_of_emails' from other contexts), the absence of differentiation is a significant gap. The agent is left without any hints about appropriate usage scenarios.

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