Poll / download a video

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

Annotations declare readOnlyHint=false but do not say why; the description supplies the reason, namely that a completed job writes an MP4 to CARPE_OUTPUT_DIR (falling back to the temp dir) and returns the path, plus the 'Free' cost note. It does not explain what is returned while the job is still running or what happens if the same job is polled again after download, so the idempotency claim stays unelaborated.

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 sentences, both front-loaded with the action and the side effect, with zero filler. The destination and return value are packed into the same clause rather than padded out.

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?

There is no output schema, so the description must explain returns, and it does: the local file path. Combined with the destination resolution rule, the default wait behavior from the schema, and the cost note, an agent has what it needs for a two-parameter polling tool.

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 only 50%: wait_seconds is documented in the schema with a default of 60, but job_id has no schema description at all. The description compensates by establishing that job_id comes from carpe_video_generate, which is the provenance an agent actually needs, though it adds nothing about format or constraints.

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 gives a specific verb and resource ('Check a video job', 'downloads the MP4') and ties the tool to its producer, carpe_video_generate. That linkage plus the video-specific naming cleanly separates it from the sibling status tools carpe_image_status and carpe_music_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?

It states the context of use: poll a job created by carpe_video_generate, and the schema notes 'Poll later with the status tool' for deferred checks. It never names an explicit alternative or a when-not-to-use condition, so it stops short of full routing guidance.

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