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

Annotations cover the mutation and open-world profile, but the description adds almost nothing behavioral: it does not say whether a job is created asynchronously, whether credits are consumed, or that the result must be fetched later. 'Keeping good quality' is a marketing reassurance rather than actionable behavior.

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 short sentence with the outcome front-loaded and no filler. It is efficient, though it spends its only clause on an unverifiable quality claim rather than routing 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 three-parameter, non-idempotent mutation with no output schema, the description omits the critical fork between supplying video_url and source_id, and does not describe what the caller receives or how to track the result. The structured data covers parameters but leaves the workflow opaque.

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%, and the schema itself explains the level enum semantics and the source_id versus video_url exclusivity. The description adds no meaning beyond that, so the baseline of 3 applies.

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 specific verb and resource (reduces file size of a video) and implicitly separates itself from siblings like resize_video or convert_video by focusing on compression. It does not explicitly name a sibling to distinguish against, 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?

There is no guidance on when to choose compression versus resize_video, convert_video, or make_gif, and no mention of prerequisites such as needing an upload or an existing job. The agent must infer the use case from the name alone.

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