Get Company-Level Contexts

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

Beyond the readOnlyHint annotation, the description explicitly states the operation is read-only and changes nothing. It also discloses failure modes (401, 403, 404), which is valuable behavioral context not present in annotations. The statement about returning a single JSON object is a minor ambiguity but does not negate the transparency gained.

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 moderately long but well-structured, leading with the core purpose and then detailing defaults, error behavior, and API endpoint. It packs useful information without excessive fluff, though it could be tightened by removing redundant statements like 'Required parameters: company_id' when the schema already declares it.

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?

With 8 parameters and no output schema, the description covers pagination, filtering, defaults, read-only nature, and error codes. However, it claims 'Returns a single JSON object' which contradicts the 'Returns all company-level contexts' earlier and the listing nature of the endpoint. This ambiguity leaves the return contract unclear.

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, but the description adds a contradictory statement: it says company_id is required yet also defaults when omitted. This directly conflicts with the schema's required field and misleads the agent about parameter usage. The description otherwise adds little beyond the schema.

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 the tool returns all company-level contexts with pagination and filtering, using a specific verb and resource. It mentions the full field set and read-only behavior, which helps distinguish it from create/update/delete siblings, though it does not explicitly contrast with get_company_level_context_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?

It provides a usage context ('Use this when you already know which company-level context you want and need its full field set') and notes that company_id defaults to procore_set_config. However, it does not mention alternatives like get_company_level_context_by_id or list-related exclusions, and the guidance is slightly contradictory as the tool returns all contexts but says use when you know the one you want.

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