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

Annotations only indicate readOnlyHint=false, idempotentHint=false, and destructiveHint=false. The description adds critical behavioral context beyond these: both choices resume the original animation request at normal video cost, accepted generated poses are reused without another review, and imported generation preserves source rendering. No contradiction with annotations exists.

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 longer than typical but the length is justified by the branching logic. It front-loads some contextual background before the direct 'Use this tool only when...' instruction, which slightly delays the core routing guidance, but every sentence contributes useful decision-making 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 no output schema and three parameters with conditional semantics, the description is remarkably complete. It covers both possible states (poseReview present vs absent), the exact user interaction required, how to submit the choice, when to cancel instead, and the downstream consequences of approval.

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?

Although schema coverage is 100%, the description enriches parameter meaning substantially. It explains exactly when choice='generated' is acceptable ('only after they accept that exact pose'), that choice='original' is used for technical failure continuation, and that poseVersion must be the exact poseReview.version shown to and approved by the user.

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's function: approve an automatic pose fallback decision. It also specifies the exact trigger condition ('Use this tool only when get_job returns a pending automaticPoseFallback'), which distinguishes it from sibling tools like approve_directional_poses and cancel_job.

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 explicit usage guidance: when to call the tool, how to branch on the presence of poseReview, which choice to submit in each scenario, and when to use cancel_job instead. It also warns 'Never approve automatically,' making the human-in-the-loop requirement unambiguous.

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