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. It states 'Create' (implying a mutation/write operation) but does not clarify permissions required, whether it's idempotent, what happens on duplicate titles, or the response format (e.g., returns the created template ID). The HTTP method (POST) hints at creation, but lacks details on error conditions, rate limits, or side effects. 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 concise, consisting of a single sentence followed by technical details. It avoids unnecessary verbosity. However, the front-loaded information is minimal (just the tool name restated), and the technical path adds value but could be better integrated. It earns a 4 for efficiency but loses a point because the first part is redundant.

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 creating a template (likely involving multiple steps or dependencies), the description is insufficient. No annotations exist to clarify safety or behavior, and there is no output schema to describe the return value. The description fails to address what a successful creation entails (e.g., template ID returned) or how it fits into broader workflows, leaving significant gaps for an agent to understand the tool's role.

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., 'company_id: Unique identifier for the company'). The description adds no parameter-specific information beyond the schema. However, since the schema is well-documented, the baseline score of 3 is appropriate—the description does not compensate but does not need to, as the schema already provides adequate semantics.

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 Company Action Plan Templates' is a tautology that restates the tool name with minimal elaboration. It lacks specificity about what 'create' entails (e.g., defining template structure, assigning approvers) and does not differentiate from sibling tools like 'create_company_action_plan_template_item' or 'create_company_action_plan_template_section', which might handle sub-components. The addition of '[Project Management/Action Plans] POST /rest/v1.0/companies/{company_id}/action_plans/plan_templates' provides technical context but does not clarify the functional purpose beyond the name.

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 does not mention prerequisites (e.g., needing an existing company or action plan type), exclusions, or related tools like 'create_company_action_plan_templates_v1_1' (a sibling) or 'create_company_action_plan_template_item' for adding items to templates. Without such context, an agent cannot make informed decisions about tool selection.

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