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

Annotations already declare read-only, idempotent, non-destructive, so the safety profile is covered; the description adds the non-obvious behavior of the pending state (poll after ~a minute) and the success payload (a mediaId to attach to a post). The anti-hallucination warning about fabricating media ids is behavioral guidance an agent cannot get from structured fields.

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 short sentences, front-loaded with the purpose and the identifier to supply, then the retry rule, then the downstream use. Every sentence carries a distinct instruction with no restatement of the name or title.

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 does the necessary work of saying what a completed job returns (mediaId). It stops short of describing failure, expiry, or cancellation outcomes for the jobId, which an agent polling a long-running generation would plausibly need.

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 schema's own text ('The jobId generate_video returned') is essentially identical to the description's 'Pass the jobId it returned', so no new semantics are added. Baseline 3 applies for a single fully documented parameter.

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 check ('whether a video generate_video started is ready') and ties the tool to its producer sibling generate_video, while naming the downstream consumers (save_draft, edit_post, create_post). An agent can distinguish this polling tool from generate_video and get_media without opening any schema.

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?

Gives explicit when-to-use ('pass the jobId it returned'), a concrete retry policy ('wait about a minute and ask again'), and two hard exclusions ('never generate it a second time and never make up a media id'). It also names the follow-up step once ready, so routing both before and after the call is covered.

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