claude_approval

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

The description adds behavioral context such as the conditional nature of respond and the content returned by inspect, but with no annotations provided, it omits details on side effects, failure modes, or rate limits, which are needed for a mutation tool.

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 front-loaded with the tool's purpose and is reasonably concise, though the Japanese phrasing could be streamlined; it effectively communicates the core functionality without verbosity.

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 output schema exists, the description adequately covers the main use cases but lacks guidance on error handling, prerequisites (e.g., an active turn), and behavior when respond conditions are not met, leaving some completeness gaps.

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?

The description adds meaning beyond the schema by explaining the flow: inspect retrieves digest and safe choices, respond sends only when conditions match. It clarifies the role of session_id and operation_id for turn correlation, complementing the 60% schema description 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?

The description clearly states it is a dedicated surface for inspecting and responding to permission confirmation UI during managed Claude's active turn, distinguishing it from sibling tools like diagnostics or pty operations.

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 explains when to use inspect (to retrieve screen digest and safe Yes/No) and respond (only if same operation and digest are displayed), providing clear context for action selection, but does not explicitly list exclusion criteria or compare to alternatives.

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