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 implies a destructive operation ('Remove') but doesn't clarify if this is reversible, what permissions are required, or the effect on related data (e.g., does it dissociate equipment from a project?). The API endpoint suggests it's a DELETE operation, which hints at mutation, but behavioral details like idempotency, error conditions, or side effects are missing. This is inadequate 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 a single run-on sentence that mixes purpose with technical endpoint details, making it poorly structured. It's not front-loaded with clear intent; instead, it buries the action in a verbose API path. While brief, it's inefficient—the endpoint clutter doesn't aid an AI agent in understanding the tool's function. It fails to prioritize human-readable information over implementation details.

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 tool's complexity (a destructive operation with three parameters), lack of annotations, and no output schema, the description is insufficient. It doesn't cover the outcome (what 'removing' entails), success/error responses, or typical use cases. The agent would struggle to invoke this correctly without guessing about behavior. The description should compensate for missing structured data but does not.

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 (e.g., 'Equipment Id', 'The Id of the project'). The description adds no parameter semantics beyond the schema—it doesn't explain relationships between parameters (e.g., equipment_id must belong to the company_id) or provide examples. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, but the description contributes no additional value.

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 'Remove current project (Project). [Core/Equipment] DELETE /rest/v2.0/companies/{company_id}/projects/{project_id}/equipment_register/{equipment_id}/current_project' is vague and tautological. It restates the tool name ('Remove current project') without clarifying what 'current project' means in this context (likely a project association for equipment). The inclusion of the API endpoint adds technical detail but doesn't improve semantic clarity. It distinguishes somewhat from siblings like 'remove_current_project_company_v2_0' by specifying '[Core/Equipment]' and the endpoint path, but the core purpose remains unclear.

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., equipment must be associated with a project), conditions for removal, or what happens after removal. Given the sibling tools include 'remove_current_project_company_v2_0' and 'remove_current_project_project_v2_1', the lack of differentiation is a significant gap. The agent is left with no usage context.

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