Get All Defects

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds beyond annotations by specifying default behavior for company_id/project_id, error payload details (401/403/404), and explicitly stating 'Read-only — it changes nothing in Procore.' This is valuable context, though the conflicting return-type statement reduces clarity.

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 unnecessarily long and contains contradictory statements (list vs. single JSON object). It front-loads the primary purpose but then introduces confusing 'single defect' language. The structure is scattered—mixing usage guidance, defaults, return type, error handling, required params, and API location—making it harder to parse than necessary.

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 output schema and 15 parameters, the description should clarify pagination and return value shape. It states 'paginated list' but then incorrectly claims 'Returns a single JSON object.' There is no explanation of how page/per_page interact with the response, nor any detail on filter parameter usage. The error handling and endpoint info are helpful, but the misleading return-type statement leaves a critical gap.

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 coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining that company_id and project_id default to the values set by procore_set_config when omitted, which is useful contextual information not present in the schema. Other parameters are already well described in the schema, so this is a solid supplement.

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 clearly states 'Returns a paginated list of defects for the project', giving a specific verb and resource. However, it later says 'Use this when you already know which defect you want' and 'Returns a single JSON object describing the defect', which directly contradicts the list nature and muddles the purpose. It does not clearly distinguish from sibling tools like get_defect_by_id.

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 usage context by explaining that company_id and project_id default to values from procore_set_config when omitted. However, the primary usage guidance—'Use this when you already know which defect you want and need its full field set'—is misleading for a list-all tool and suggests a single-fetch use case. No alternatives or exclusions are mentioned.

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