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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavioral context: the two-phase, state-dependent call protocol and the privacy-relevant fact that 'the server never receives the recording itself'. Those are the details an agent needs to operate the tool correctly and are not derivable from annotations or schema.

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 sentences, front-loaded with the core action, then the call protocol, then the data-handling note. The middle sentence is a dense comma list of return values, but every element is informative and nothing is redundant padding.

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 carries the return-value burden and does so for both call modes, listing crop chrome, beat start times, camera target, and Remotion code. For a tool with a deeply nested `measurements` object, slightly more on what the probe script measures or how to round-trip its output would round this out, but coverage is strong.

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 75% and the description explains the pivotal `measurements` parameter beyond the schema's one-line note — it clarifies that omitting it yields the measurement script and supplying it yields the cut, which is the real semantics of that field. It adds nothing for `fps` or `maxBeats`, but those are low-complexity scalar settings with schema defaults.

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+resource ('cuts a screen recording into beats') plus the product context (a Remotion film) and the concrete outputs (crop chrome, beat start seconds, camera direction, Remotion code). This is clearly distinguishable from siblings like render-video-frames or plan-video, which do not analyze a recording's content.

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?

The description effectively documents the required two-step workflow: the first call (no measurements) returns a probe script, the second call (with measurements) returns the cut. That sequencing is critical usage guidance an agent could not infer. It stops short of explicitly routing against alternatives or stating exclusions, so it is not a 5.

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