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

Annotations only cover readOnly/openWorld, so the description earns credit for disclosing what actually matters here: a paid x402 call ($0.48 USDC), per-character narration pricing, the Deepgram Aura voice provider, caption burn-in, and the 30-image ceiling. It stops short of render latency, accepted image formats, or whether payment failure is recoverable.

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?

One front-loaded sentence: purpose first, then input constraints, output options, and cost. Dense but every clause is informative. The pricing clause is slightly muddled (a per-character rate plus a flat USDC figure that do not obviously reconcile), which costs it a point.

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 9-parameter paid generation tool with no output schema, the description covers purpose, inputs, output container (MP4), orientation, and price — enough to call it correctly. Remaining gaps are the default delivery mechanism (inline base64 vs link) and duration control via seconds_per_image.

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 44%, so the description must carry part of the load. It adds real meaning for images (the 1-30 cap that the bare string array lacks), narration, and audio_url as an alternative narration source, and implies captions/size behavior. It says nothing about seconds_per_image or the practical effect of store/format beyond what the schema already states.

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+resource (make a video) and immediately bounds it: 1-30 images plus a narration script or supplied audio, burned-in captions, MP4 output in three named aspect ratios. An agent can distinguish it from image_generate, media_convert, or audio_speech 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?

The description makes the required input shape clear (you need images, optionally narration or audio_url), which implies when the tool applies, but it never names alternatives or exclusions — e.g. it does not say to use image_generate for stills or media_convert for reshaping an existing clip. Usage is implied rather than stated.

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