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

Beyond the annotations (readOnly, idempotent, non-destructive, open-world), the description discloses the return shape per media type — images come back viewable, video/wav only as type, size and URL — and the key operational trait that Google-hosted files are temporary and an expired one answers 404. That 404/expiry detail is exactly the behavior an agent cannot infer from annotations and needs in order to handle failures correctly.

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?

It is a single front-loaded sentence that opens with the action and ends with the endpoint, with no padding or restatement of the title. The clause stacking around return types is a bit dense but each clause carries distinct information, so nothing is wasted.

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 describing return values and does so per media type, and it covers the failure mode (expired file = 404) for a one-parameter read tool. Only minor gaps remain, such as whether the returned URL itself is time-limited or whether any auth scope applies.

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%, so the parameter is already documented, but the description adds real meaning by stating where a valid mediaId comes from (a job result or an avatar's previewMediaId) rather than the generic 'A video, image or audio (speech) mediaId' in the schema. That provenance guidance is genuine added value on top of the baseline.

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 mediaId ... and get its download URL') plus the underlying endpoint GET /media/{mediaId}, and it lists the two places a mediaId originates (a job result or an avatar's previewMediaId). That distinguishes it clearly from the sibling creation/list tools, which never return a single media artifact.

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 tells the agent when to reach for this tool by naming the upstream sources of a mediaId (job result, avatar previewMediaId), which implicitly routes the agent through vids_get_job or vids_list_avatars first. It stops short of naming alternatives explicitly or saying when not to use it, so it is clear context rather than full when/when-not guidance.

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