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 'Show' (implying a read operation) and includes a GET endpoint, suggesting it's safe and non-destructive. However, it doesn't disclose any behavioral traits like authentication requirements, rate limits, error conditions, or what the output looks like (e.g., JSON structure). The description adds minimal context beyond the endpoint, leaving the agent with significant gaps in understanding how the tool behaves.

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 tautological purpose statement and an API endpoint. However, it's not effectively structured—the key information (that this retrieves a single timecard by ID) is buried in the endpoint pattern rather than stated upfront. The bracketed domain context is useful but doesn't earn its place in a tool description meant for an AI agent. While not verbose, it lacks the front-loaded clarity needed for quick comprehension.

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) and the absence of both annotations and an output schema, the description is incomplete. It doesn't explain what a 'Time And Material Timecard' is, what data it returns, or how pagination works (since page/per_page are optional but not required). For a tool that likely returns structured data, the description fails to provide enough context for the agent to use it effectively without relying heavily on the schema alone.

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 (id, project_id, page, per_page) well-documented in the schema. The description adds no parameter semantics beyond what the schema provides—it doesn't explain relationships (e.g., that id is the timecard ID within the project) or usage (e.g., that page/per_page are for pagination). Since the schema does the heavy lifting, the baseline score of 3 is appropriate, but the description misses an opportunity to clarify parameter interdependencies.

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 Time And Material Timecard' is a tautology that restates the tool name without adding clarity. It specifies the resource ('Time And Material Timecard') but the verb 'Show' is vague—it could mean display, retrieve, or list. The bracketed '[Project Management/Field Productivity]' provides domain context but doesn't clarify the specific action. Compared to sibling tools like 'list_time_and_material_timecards' (which likely lists multiple) and 'show_time_and_material_entry' (which shows a single entry), this tool's purpose isn't distinctly differentiated.

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 doesn't mention prerequisites (e.g., needing a specific project_id and id), nor does it compare to sibling tools like 'list_time_and_material_timecards' (which might list multiple timecards) or 'show_time_and_material_entry' (which shows a different resource). The inclusion of the API endpoint 'GET /rest/v1.0/projects/{project_id}/time_and_material_timecards/{id}' implies it retrieves a single timecard by ID, but this isn't explicitly stated in natural language for the agent.

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