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

Annotations already declare idempotent, non-destructive, open-world behavior, so the description's added value is the state machine: processing while rendering, depth_video_url on success, explicit failure reporting with token refund, and not_found for unknown ids. That is substantial behavioral detail, though it omits polling cadence or any rate/expiry notes for a task_id.

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?

Four tight sentences with the primary action and the create_depth_map dependency front-loaded, followed by the outcome states. Every sentence carries distinct information; nothing is repeated from the schema or annotations.

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?

With no output schema, the description carries the burden of explaining returns and does so: processing, depth_video_url, failure with token return, not_found. It is essentially complete for invoking and interpreting the call, missing only secondary details such as polling guidance or other fields in a successful response.

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 the single parameter is already documented as 'the task_id returned by create_depth_map', so baseline is 3. The description adds meaning by explaining what happens with an id that was never started (not_found) versus one still starting (processing), which helps an agent interpret rather than just supply the value.

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 (check a depth map render) and explicitly anchors it to the sibling that creates the job, create_depth_map. It also names the exact output field (depth_video_url), so an agent can distinguish this from generic status tools like get_video_status or check_job_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?

Clear usage context: use after create_depth_map and pass the task_id it returned, which is a precise when-to-use condition. It does not explicitly exclude the other status-checking siblings (get_video_status, get_audio_status, check_job_status), so the routing guidance is strong but not complete.

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