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 'Save Markups' and includes a POST endpoint, implying a write operation, but doesn't disclose behavioral traits like whether it overwrites existing markups, requires specific permissions, has rate limits, or returns a confirmation. The endpoint path suggests it saves to a specific viewer document, but this is structural rather than behavioral guidance. The description is minimal and lacks critical context for a mutation tool.

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 three elements: a tautological phrase, a category in brackets, and an endpoint. However, it's not front-loaded with useful information—the first part 'Save Markups' is redundant. The endpoint provides technical context but doesn't aid understanding. It's brief but inefficient, as the space could be used for actionable details rather than repetition and raw API paths.

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 of a mutation tool with 4 required parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what 'save' entails (e.g., create, update, or replace), the expected format of 'markups', error conditions, or response structure. For a tool that modifies data, this lack of context leaves significant gaps for an agent to operate correctly.

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 (company_id, project_id, viewer_doc_id, markups) having basic descriptions that match their names. The description adds no additional meaning about parameters beyond what the schema provides (e.g., format of markups array, relationships between IDs). With high schema coverage, the baseline is 3, as the description doesn't compensate with extra insights.

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 'Save Markups' is a tautology that restates the tool name without adding clarity. It includes a category '[Project Management/Document Markup]' and an endpoint 'POST /rest/v1.0/companies/{company_id}/projects/{project_id}/viewer_documents/{viewer_doc_id}/markups', which hints at saving markups to a document in a project context, but lacks a specific verb-resource statement like 'Save an array of markups to a specified viewer document in a project.' It doesn't distinguish from sibling tools like 'add_a_new_markup' or 'modify_markups'.

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., existing document), exclusions, or compare it to sibling tools such as 'add_a_new_markup' or 'modify_markups'. Without this, an agent cannot make an informed choice among similar tools.

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