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

Annotations already establish this is a non-read-only, non-destructive, closed-world operation, and the description usefully adds the write-scope requirement, the output file naming and placement beside the source video, and input constraints (one frame, three to five words, at most one picture). However, "Free: nothing is charged" directly conflicts with the budgetUsd parameter documented as defaulting to 2 with a max of 10, which muddies the cost model for the agent. That internal inconsistency keeps this at a 3 rather than higher.

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, each carrying distinct information: composition inputs, artifact location, cost, and authorization. The key output convention is front-loaded among the constraints. No filler or restatement of the tool name.

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?

An output schema exists, so return shape need not be described, and the description covers the artifact naming, required scope, and input limits well. Gaps remain for a nine-parameter mutation tool: whether rendering is synchronous or job-based, what happens when a thumbnail already exists for the video, and a cost model that reconciles the "free" claim with budgetUsd.

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 description coverage is 100%, so the schema already explains all nine parameters including frame_at semantics, headline star-marking, frame_key, and the colour fields. The description restates the headline word count and the single-picture limit, which duplicates rather than extends the schema. The cost claim it adds is misleading rather than clarifying, so no credit above 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?

The description names the specific action and artifact: composing a cover image for a finished video from one frame, a short headline, and optionally a picture, saved as <video>-thumbnail.jpg. The phrasing is deliberately stylized ("Package a finished video with its cover"), which is slightly less direct than a plain verb+resource statement, but an agent can still identify the operation immediately. It does not explicitly contrast with render_carousel or generate_image, so it stops short of a 5.

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?

Usage is implied rather than stated: it is for videos you intend to publish ("so a post that carries the video key gets the cover") and it requires write scope. There is no explicit when-not guidance and no named alternative for adjacent tasks such as carousel covers or standalone image generation. Adequate but the agent must infer the boundaries.

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