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

Annotations already cover the safety profile (non-readOnly, non-destructive, closed-world, non-idempotent), so the description's added value is the credit cost ('Uses 1 video, on every plan') and the hard input limits, which are exactly the facts an agent needs before spending a credit. It does not say what is returned on success/failure or what happens to the source audio.

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?

The core definition and the input contract come first, and each later sentence carries actionable detail. The ffmpeg command and the 'New video → Use your audio' UI hint are on the verbose side but still earn their place as fallback paths.

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 5-param, zero-required, no-output-schema generation tool, the description covers input format, size, duration, credit cost, and a manual alternative — enough to call it correctly. The gaps are the ambiguous style/Paper Collage relationship and any statement about the returned artifact.

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 80% schema coverage the baseline is 3, but the description adds real constraints for audio_url and audio_base64 (WAV/PCM, mono preferred, duration window, size cap) and clarifies that exactly one of the two should be supplied, which the schema does not express since nothing is required. It leaves the style enum and the project parameter unexplained, and 'Uses 1 video (Paper Collage 2)' sits uneasily beside a five-value style enum, leaving the agent unsure whether style is actually selectable.

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 plus the key differentiator from the sibling make_video: the user's own recording is the voice and no synthetic voice is generated. The 'no synthetic voice' phrasing lets an agent route between this and make_video without opening either 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 concrete acceptance conditions (WAV PCM 16-bit, mono preferred, 3s–1:30, ≤20 MB) and an escape hatch with an exact ffmpeg command for other formats, plus a pointer to in-app recording. It never explicitly says 'use this instead of make_video when the user already has audio', so the alternative-routing is only implied.

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