Create Project Insurance

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

Annotations only convey readOnlyHint=false, idempotentHint=false, and destructiveHint=false. The description adds substantial behavioral context: returns HTTP 201 with a new id, repetition creates additional records (non-idempotency confirmation), and failure modes with specific status codes (401, 403, 404). It also clarifies the payload transformation and config-driven project_id default, going well beyond the annotations.

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?

Every sentence in the description earns its place: purpose, argument handling, parameter default, return behavior, non-idempotency, error conditions, required parameters, and API endpoint. No filler or redundancy; the structure flows logically from operation to invocation details to expectations.

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?

Despite having 18 parameters and no output schema, the description is complete for a create operation. It covers purpose, request construction, response characteristics, failure modes, required fields, and the specific Procore API endpoint. The schema handles parameter details, so the description need not enumerate them. This is a well-rounded, actionable description.

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 has 100% coverage of 18 parameters and already documents each field. The description adds meaning by explaining that record fields must be passed as top-level arguments despite being nested under 'insurance' in the actual request payload—critical for correct invocation. It also clarifies that project_id can be omitted and defaults from procore_set_config, which is not apparent from the schema's required list.

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 begins with 'Create a new Insurance associated with the specified Project,' which is a specific verb+resource statement that clearly distinguishes this from sibling tools like update_project_insurance, list_project_insurances, and delete_project_insurance. It also clarifies non-idempotent behavior with 'calling it again creates another record,' reinforcing its unique create semantics.

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 clear invocation context including top-level argument handling, the 'insurance' nesting behavior, project_id defaulting via procore_set_config, and required parameters. It does not explicitly contrast with alternatives (e.g., 'use update_project_insurance to modify'), but the create intent is unmistakable and the operational details are sufficient for correct use.

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