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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds useful value by disclosing the success return (an MP4 link to share with the user), but it never describes what is returned while the job is pending or failed — the state most likely to be hit on a first poll.

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?

Two short sentences, zero filler, with the action stated first and the payoff (MP4 link) second. Nothing could be removed without losing 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?

For a one-parameter read tool with rich annotations, the description covers the essential outcome. The only real gap is the pending/failed state behavior, which matters for an async status check since there is no output schema to document the status field.

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?

With one parameter and 100% schema description coverage, the schema already explains that job_id comes from generate_video. The description repeats that origin but adds no format, validity, or reuse details, so the baseline of 3 applies.

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 (check) and resource (a video job) and ties it explicitly to the generate_video sibling, which is the origin of the job_id. It stops short of distinguishing itself from list_generations, which could also surface video job state, but the purpose is unambiguous.

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 phrase 'a video job from generate_video' implies the usage context (call after generate_video), but there is no explicit when-to-use, no polling guidance, and no statement of what to do instead while the job is still running. Usage is inferable rather than stated.

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