로컬 피드백 삭제

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

Although the annotations already indicate destructive=true and readOnly=false, the description adds crucial behavioral context: it deletes only the local copy, not the remote one, and requires explicit user confirmation. This goes beyond the annotations and informs the agent of the exact side effects and prerequisite.

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 concise, with no redundant words or unstructured extras. It conveys the core action, the scope, and the confirmation requirement in two clear sentences.

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?

The description provides sufficient context for an agent to decide when to call the tool: it knows what will be deleted, what will not, and the mandatory confirmation step. No output schema is needed for a delete operation, and the given information is adequate for correct invocation.

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% and both parameters are well described. report_id is clearly tied to get_feedback_status receipts, and confirm_discard is explained as requiring explicit user confirmation. These descriptions add meaning beyond just the parameter types and patterns.

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 deletes a local feedback copy identified by a receipt number, explicitly distinguishing it from remote copies. The verb 'delete' is specific and the resource is well-defined, making it distinct from sibling tools like retry_feedback_delivery or get_feedback_status.

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 that only the local copy is deleted and that remote copies are not affected, and it mandates that the user must be informed and explicitly confirm before execution. This provides clear guidance on when and how to use the tool, though it does not explicitly contrast with sibling tools.

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