check_video

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

Annotations already declare readOnlyHint=true, so the safety profile is covered and the description's job is to add context — which it does by explaining why a finished-file check differs from a still. It does not disclose cost or latency (frame extraction is likely expensive), behavior when the file is absent, or the shape of the returned metrics. Adequate but with clear gaps beyond the annotation.

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, front-loaded with the return payload before the rationale and the parameter tip. Nothing is redundant. The phrase 'For counters pass adjacent times' is compressed to the point of needing domain knowledge to parse.

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 no output schema, the description's enumeration of size/length/loudness/frames is doing useful work in place of one. But for a read-only inspection tool with an undocumented required `project` parameter and four distinct returned metric families, an agent still lacks the return format and how to target the right project.

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 0%, so the description must carry parameter meaning: it adds genuinely useful guidance for `times` ('For counters pass adjacent times') that the schema does not convey. However, the required `project` parameter is never mentioned, the `file` default of final.mp4 is unaddressed, and the 8-item cap on `times` is left unexplained.

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 concrete outputs (size, length, loudness, frames) of inspecting a finished video file, which tells an agent exactly what the tool returns. It implicitly separates itself from the `stills` and `render` siblings by explaining that a render differs from a still. The verb itself is elided in the opening noun phrase, leaving the action slightly implicit.

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 a real when-to-use rule: verify the actual rendered file rather than trusting a still, because stills skip motion blur, which effectively routes the agent away from `stills`/`preview`. It also supplies a conditional instruction for sampling ('For counters pass adjacent times'). It stops short of stating exclusions for `render_status` or what to do before a render completes.

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