Check a video

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

Goes well past the annotations by disclosing a cost model (loudness, black and frozen checks are free; the on-screen text and element read is a small paid frame read, and frames:false skips it), the no-re-render guarantee, and the shape of output (each issue carries a Fix line). readOnlyHint=false is consistent with a credit-consuming, open-world check rather than contradicted. This is exactly the cost/side-effect context annotations cannot express.

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 the gating condition and the check list before cost details, and every clause carries information. It is dense and packed into one long paragraph, so the cost model and assertion syntax are harder to scan than they would be as separate lines.

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 and no annotations covering cost or side effects, the description carries the load and does: what is checked, what assertions are accepted, what each result includes (a Fix line), and what costs credits. The only unstated item is whether the call returns synchronously or as a job to poll, which is minor for a bounded check.

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, but the description adds real meaning: the -14 LUFS default for loudnessTarget, the purpose of frames:false as the paid-read toggle, and the four assertion kinds spelled out with their argument shapes ({element, bySec}, {a, b}, {element}, {maxStaticSec}). The bare a/b string fields in the schema are only partially clarified, which keeps it at 4 rather than 5.

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 a finished video") and enumerates the exact mechanical checks performed: loudness vs target, true peak, black/frozen stretches, safe-band caption/text placement, text off-frame. It also rules itself out of the render pipeline ("never re-renders"). It stops short of a 5 because it never distinguishes itself from the neighbouring analyze_video, score_ad, or diagnose_posts tools, which an agent must still disambiguate on its own.

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 gating is given on both sides: use it "ONLY when the user asks" and "never after every render", which prevents an agent from calling it reflexively after every render job. What is missing is routing to alternatives — nothing says when analyze_video or score_ad should be preferred over this check.

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