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 mentions 'List' and an API path, implying a read-only operation, but doesn't disclose behavioral traits like pagination behavior (page/per_page parameters), rate limits, authentication needs, or error conditions. The description lacks details on what the tool returns (e.g., column metadata vs. data) and any side effects. It's minimal and misses key operational context.

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 two parts: a functional statement and an API path. It's front-loaded with the core purpose. However, the API path could be considered redundant if the tool name already implies it, and it lacks structuring for readability (e.g., bullet points). It's efficient but could be slightly more polished.

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 (4 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain the return format (e.g., list of column objects with names/types), pagination details, or error handling. For a tool with parameters like page/per_page, more context on output behavior is needed. The API path adds some context but insufficient for agent invocation.

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., 'Budget View ID', 'Unique identifier for the project.'). The description adds no parameter semantics beyond the schema, not explaining relationships (e.g., budget_view_id must belong to project_id) or constraints (e.g., per_page max 100). Since schema coverage is high, the baseline is 3, but the description doesn't compensate with additional 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 'List Budget Detail Columns' states the action ('List') and resource ('Budget Detail Columns'), providing a basic purpose. However, it's vague about scope (e.g., what columns are included) and doesn't differentiate from sibling tools like 'list_budget_details' or 'list_budget_detail_filter_options', which are also list operations in the same domain. It adds an API path '[Construction Financials/Budget] GET /rest/v1.0/budget_views/{budget_view_id}/budget_detail_columns', which clarifies the endpoint but doesn't enhance the functional purpose.

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 valid budget_view_id and project_id), exclusions, or comparisons to sibling tools like 'list_budget_details' (which might list rows instead of columns). The API path hints at a budget view context but doesn't explicitly state usage context.

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