Procore MCP Server

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It implies a read operation ('Retrieve') but the PATCH method suggests a state change (likely restoring). The description doesn't clarify if this is a mutating operation, what permissions are required, side effects, or response format. It leaves critical behavioral traits undocumented.

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 brief and front-loaded with the core action. However, it wastes characters on the HTTP endpoint which is redundant for an AI agent. The single sentence is efficient but could be more informative without sacrificing conciseness.

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 no annotations, no output schema, and a PATCH operation implying mutation, the description is incomplete. It doesn't explain what 'retrieve' entails (e.g., restoring a soft-deleted item), the outcome, error conditions, or relationship to other recycle bin tools. For a mutating tool with 3 parameters, this is inadequate.

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. The description adds no parameter semantics beyond the endpoint path hinting at 'restore' action. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, though the description doesn't compensate for any gaps.

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 'Retrieve Recycled Witness Statement' is a tautology that essentially restates the tool name. It adds minimal context with '[Project Management/Incidents]' and the HTTP endpoint, but fails to specify what 'retrieve' means in this context (e.g., restore from recycle bin, fetch metadata). It doesn't clearly distinguish from sibling tools like 'retrieve_recycled_witness_statement' (without version) or 'list_recycled_witness_statements_v1_1'.

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 recycled witness statement), exclusions, or related tools like 'restore_recycled_witness_statement' or 'destroy_witness_statement'. The agent must infer usage from the endpoint path alone.

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