Render a video thumbnail

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

Annotations only declare the write/no-destroy profile; the description goes further by disclosing the budget hold-and-release semantics ('budgetUsd ... is held while it runs and released'), the max of 10, the write-scope requirement, and the output file location beside the video. It does not cover failure modes or what happens if the job is cancelled, but the added cost and auth context is substantive.

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?

A single tight paragraph: core action first, then output artifact/location, then cost, then scope requirement. Every clause carries information and there is no filler.

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 an output schema present, return values need not be explained, and the description covers the artifact name, its relationship to posts, cost, and auth scope. Remaining gaps — what 'Free' precisely means when a budget is held, and error/retry behavior — are modest for this complexity level.

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 every parameter is already documented, and the description largely repeats it (frame_at in seconds, three-to-five-word headline, one picture). The only marginal additions — 'at most one picture' and the post-key consumption behavior — are minor, so the schema is doing the heavy lifting.

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 a concrete verb and artifact: it packages a finished video with a cover frame, a short headline, and at most one picture, and files the result as <video>-thumbnail.jpg. That is clearly distinct from siblings like generate_image, render_carousel, or brand_mark, though it never explicitly contrasts itself with them.

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 gives implied usage context — 'a post that carries the video key gets the cover' — which tells the agent what the output is for. However, it offers no explicit when-to-use versus when-not-to-use guidance and never names an alternative thumbnail/cover route, so the agent must infer the trigger conditions.

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