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

With no annotations, the description carries the full burden. 'Optional cleanup' hints at side effects but does not say whether it deletes data, frees capacity, is idempotent, or requires preconditions. The actual behavior after calling retrieve is not disclosed.

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 front-loaded sentence with no filler words and easy to scan. It loses a point only because the brevity sacrifices semantic completeness, though that is largely a completeness concern.

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 lifecycle tool with no annotations and no output schema, the description leaves major gaps: side effects, return value, idempotency, and relationship to video_retrieve are all unstated. The single parameter is covered, but the operation itself is under-specified.

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 the baseline is 3; the description adds no parameter meaning beyond the schema. It does not reinforce that queue_id is the identifier returned by video_queue or generate_video.

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 endpoint and says 'optional cleanup after retrieve,' which gestures at the action but never states what 'complete' actually does or what resource is affected. It does not clearly distinguish itself from siblings like video_retrieve or wait_for_video beyond the vague 'after retrieve' timing.

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 provides some usage context by indicating the tool is optional and should follow retrieve. However, it gives no when-not-to-use guidance, no alternatives, and no conditions that would make cleanup necessary or unnecessary.

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