Post Instances Customers Rfi

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

Annotations already declare this as a non-read-only, non-idempotent write, so the bar is lower; the description still adds real value by disclosing the side effect (kyc_status flips back to verifying) and the soft-failure return shape { success: false, reason }. It leaves unaddressed whether the kyc_status transition triggers downstream review steps or how partial/invalid RFI answers are handled.

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?

Three short sentences, action first, side effect second, failure handling third — nothing is padded and every clause carries operational information for the caller.

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?

For a mutation with a free-form nested body, no output schema, and 50% param coverage, the description covers the action, the state change, and the non-error failure path. The remaining gap is what the flat response body should contain, which is the one thing an agent still has to guess at.

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 50% and the undocumented parameter is requestBody, which the schema leaves as an open free-form object. The phrase 'flat response object' does add a hint about that body's shape, but no field-level semantics, required keys, or type expectations are given. Baseline 3 applies given partial schema coverage.

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?

States a specific verb and resource ('Submit a flat response object for the open RFI') and implicitly separates itself from the read-side sibling GetV1InstancesCustomersRfi by naming the response-submission action. An agent can tell this is the write counterpart to the RFI read endpoints without opening any schema.

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?

Gives a concrete conditional path for failure ('when no pending RFI exists, callers should refetch the RFI state instead of retrying'), which is exactly the kind of branch an agent needs. It does not explicitly name the GetV1InstancesCustomersRfi/GetV1InstancesRfi tools to refetch with, so routing requires a small inference.

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