⚠️ CPA: complaint by actionId

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

The description discloses that the complaint is irreversible and cannot be withdrawn, aligning with the destructiveHint: true annotation. It also mentions a rate limit of 3 requests/min and that confirmation is required by default, adding behavioral context beyond annotations without contradiction.

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 very concise, using bullet points effectively. Every sentence adds value: purpose, irreversibility, prerequisite, preference over sibling, and rate limit. No redundant or irrelevant information.

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 tool has 4 parameters, no output schema, and annotations indicating destructive action, the description covers the required context: irreversible nature, prerequisite actionId, preferred sibling, and rate limit. It does not explain return values, but that is acceptable without an output schema.

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%, so the schema already documents all parameters thoroughly. The description reinforces the importance of actionId from preceding calls and provides context for dryRun and idempotencyKey usage, but does not add new semantic meaning 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 files an external complaint against a CPA target action by actionId to dispute a charge. It specifies the type of action (call or chat) and distinguishes from the sibling tool cpa_post_create_complaint by noting it covers both calls and chats, making the purpose very specific.

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 explains when to use (to dispute off-target charges), the prerequisite of obtaining actionId from specific tools (cpa_chats_by_time_v2 / cpa_get_calls_by_time_v2), and indicates preference over a sibling tool. It does not explicitly state when not to use, but the context is clear.

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