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 states 'List Custom Tool Users' and includes an HTTP GET endpoint, implying a read-only operation, but doesn't explicitly confirm safety (e.g., no destructive effects), discuss permissions ('Company Admin/Custom' is vague), rate limits, or pagination behavior (though parameters suggest pagination). The description adds minimal behavioral context beyond the implied read action, leaving significant gaps for a tool with no 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 concise with two parts: a restatement of the tool name and an API endpoint. It's front-loaded with the core action ('List Custom Tool Users'), and the endpoint adds technical context without verbosity. However, the first part is somewhat tautological, and the structure could be improved by integrating the endpoint more seamlessly or adding a brief explanatory phrase.

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's complexity (3 parameters, no output schema, no annotations), the description is inadequate. It lacks explanation of what 'Custom Tool Users' are, the expected output format, pagination details, or error conditions. The API endpoint provides some context, but without annotations or output schema, the description fails to provide sufficient completeness for an agent to use the tool effectively, especially in a server with many similar listing tools.

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 parameter descriptions in the schema (e.g., 'project_id' as 'Unique identifier for the project', 'page' as 'Page', 'per_page' as 'Elements per page'). The description adds no parameter semantics beyond what the schema provides, not even mentioning the parameters. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description doesn't compensate but doesn't detract either.

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 Custom Tool Users' restates the tool name but adds minimal context ('[Company Admin/Custom - Configurable Tools] GET /rest/v1.0/projects/{project_id}/custom_tools/users'). It specifies the verb ('List') and resource ('Custom Tool Users'), but is vague about what 'Custom Tool Users' are and doesn't differentiate from sibling tools (e.g., other 'list_' tools). The inclusion of the API endpoint provides some specificity, but the purpose remains somewhat unclear.

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 mentions '[Company Admin/Custom - Configurable Tools]', which hints at a permission context, but doesn't explain prerequisites, use cases, or when to choose this over other user-listing tools. With many sibling tools (e.g., 'list_company_users_v1_0', 'list_project_users'), the lack of differentiation leaves the agent without clear usage instructions.

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