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. The description mentions it's a POST operation (implying mutation) and shows the endpoint structure, but doesn't disclose important behavioral traits like required permissions, whether this creates permanent records, what happens on failure, or any rate limits. The API path format provides some structural context but lacks operational guidance needed for a mutation tool with zero annotation coverage.

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 just two elements: the action name and API endpoint. It's front-loaded with the primary purpose. However, the endpoint detail could be considered extraneous since it's structural rather than behavioral information. While efficient, it under-specifies rather than being optimally concise with meaningful content.

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?

For a mutation tool with 3 required parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what kind of attachment is being created (file? reference? metadata?), what the expected response looks like, or any prerequisites. The API path provides some context about the resource hierarchy, but this doesn't compensate for the missing behavioral and operational information needed to use this tool 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 all three parameters well-documented in the schema itself. The description adds no parameter semantics beyond what the schema already provides - it doesn't explain the relationship between project_id and list_id, nor does it clarify the deprecated 'attachment' field's replacement. Since the schema does the heavy lifting with complete descriptions, the baseline score of 3 is appropriate, though the description adds no value here.

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 'Create Attachment' is a tautology that restates the tool name without adding meaningful context. It mentions the API endpoint path '[Project Management/Inspections] POST /rest/v1.0/projects/{project_id}/checklist/lists/{list_id}/attachments', which provides some resource context but doesn't clearly explain what the tool actually does beyond the obvious 'create' action. It fails to distinguish this from sibling attachment tools like 'add_attachments_to_punch_item' or 'create_checklist_item_attachment'.

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. With multiple attachment-related sibling tools present (e.g., 'add_attachments_to_punch_item', 'create_checklist_item_attachment', 'bulk_create_checklist_inspections_item_attachments'), there's no indication of what makes this specific attachment creation tool unique or when it should be preferred. The API path suggests it's for project checklist attachments, but this isn't explicitly stated as usage guidance.

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