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 for behavioral disclosure. The description mentions 'Update' which implies mutation, but doesn't specify whether this requires special permissions, whether it's idempotent, what happens to existing attachments when updating, or what the response contains. The PATCH method hint suggests partial updates, but this isn't explicitly stated. For a mutation tool with 13 parameters and no annotations, this is a significant gap in behavioral transparency.

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 extremely concise at just one line with three elements: action, category, and API endpoint. There's zero wasted space, and the information is front-loaded. However, the conciseness comes at the cost of completeness - it's arguably too brief for a tool with 13 parameters and mutation behavior. The structure is clean but minimalistic.

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 (13 parameters, mutation operation, no annotations, no output schema), the description is inadequate. It doesn't explain what a witness statement is in this context, what fields are typically updated, whether updates are audited, what permissions are required, or what the response looks like. For a mutation tool in an incident management system with many parameters, this description leaves too many questions unanswered for effective agent use.

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%, so the schema already documents all 13 parameters thoroughly. The description adds no parameter information beyond what's in the schema - it doesn't explain which fields are commonly updated together, which are required for partial updates, or provide examples of typical update scenarios. With complete schema coverage, the baseline is 3, but the description doesn't add meaningful semantic context about parameter usage.

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 states 'Update Witness Statement' which is a clear verb+resource combination, but it's very basic and doesn't distinguish from sibling tools. It includes a category tag '[Project Management/Incidents]' and API endpoint 'PATCH /rest/v1.0/projects/{project_id}/incidents/witness_statements/{id}', but these are technical details rather than functional clarification. The purpose is understandable but lacks specificity about what fields can be updated or the context of witness statements.

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. There's no mention of prerequisites (like needing an existing witness statement), no indication of when this should be used versus creating a new witness statement, and no reference to sibling tools. The API endpoint pattern suggests it updates existing witness statements, but this is inferred rather than 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.