record_clip

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

Annotations already flag this as a destructive, open-world, non-idempotent write, so the safety bar is partly covered. The description adds real behavioral detail: playback is headless, the clip is recorded for durationMs, the pages defines window.startClip() which is invoked at recording start, and readySelector waits before the clock starts. It doesn't disclose errors, rate limits, or the returned handle.

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 tight clauses, front-loaded with the action and input, then output defaults, then the optional startClip hook. Every sentence earns its place, though the input-vs-output sentence is dense and packs several unrelated facts together.

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 an 11-parameter destructive tool with no output schema and low schema coverage, the description still leaves gaps: fps and resourceWaitMs are never explained, the name vs output resolution is left to the schema, and there is no indication of what is returned (file path/handle) after recording. It is adequate but not complete.

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 only 27%, so the description must carry weight, and it does: it defines html vs url input, explains width/height defaults as vertical 1080x1920, clarifies format options and durationMs semantics. It omits fps, resourceWaitMs, and the readySelector/name/output relationships, but covers most of the functionally critical parameters.

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 ('Render a video clip from code') plus the input forms (HTML document or URL) and the output artifacts (mp4/webm/gif). This clearly separates it from browser_screenshot, browser_record_start/stop, and windows_snapshot in the sibling list.

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 explains what to pass (complete HTML document or a URL) and mentions the window.startClip() hook, which is genuine usage context. However, it never says when to choose this over browser_record_start/browser_record_stop, and it does not note that at least one of html/url is functionally required despite required=0.

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