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

Adds substantial context beyond annotations: the check takes minutes and returns a Job ID, must be awaited via wait_for_jobs, re-checking an unchanged version is free of new credits, and the cost model is spelled out (preview render at 5 credits/60s plus review at roughly 4 credits). This is exactly the cost/latency/async disclosure structured fields cannot carry.

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?

Front-loaded with purpose and mechanism, then when-to-call, then cost. Dense and mostly waste-free, though the iterate-and-recheck sentence and the caching note could be tightened against the surrounding material.

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 fully covers the return contract (a verdict plus per-problem seconds, diagnosis, and fix), the async job path, credit cost, and caching. An agent has everything needed to call it and act on the result.

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 both parameters are already well documented there, so the description need not restate them. It only lightly reinforces the projectId/job routing ('wait_for_jobs takes the projectId of the calls that started the jobs') and adds nothing about the 'request' parameter's role in shaping the review.

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?

States a specific verb and resource ('check an edit before you export it') and immediately explains the mechanism: a 540p preview reviewed for picture and sound against Vidova's quality bar. It is clearly distinguishable from render_video (export) and fix_film (repair), both named or implied by context.

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?

Explicit lifecycle guidance: call after building or changing an edit, before render_video, fix every named problem, then call again. It also names the follow-up tool (wait_for_jobs) for the async case, leaving nothing to inference.

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