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

Annotations only mark readOnly=false and openWorld=true, so the description must carry behavioral weight. It does: it discloses asynchronous execution, the generation_id return, the need to poll get_generation until 'completed', and pricing/duration limits. It omits failure/terminal status variety, but goes well beyond the annotations.

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?

Three short sentences: purpose, price/length constraint, and polling contract. Front-loaded with the core action, no filler, and every sentence adds needed operational information.

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 one-parameter tool with no output schema, the description supplies the essential async workflow and the mechanism to retrieve results. Minor gaps remain around failure statuses and file-size/format restrictions, but the schema covers the video input format and the description covers the polling path.

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?

The input schema already fully defines the only parameter (video: public https URL or base64 data URI) with 100% coverage, so the baseline is 3. The description adds no extra parameter-level detail beyond the schema.

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 opens with a specific verb and resource ('Colorize old videos') and adds practical constraints ($0.10 per video, up to 30s), so an agent knows what the tool does. However, it does not explicitly contrast with ai_photo_colorizer or other colorization/restyle siblings, so differentiation relies on the word 'video'.

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 clearly states the tool is for colorizing videos and gives the invocation pattern (returns generation_id, poll get_generation), so the intended use is implied. It does not name alternatives or say when not to use it, leaving routing to inference.

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