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

With no annotations, the description carries the full disclosure burden and meets it thoroughly: it discloses the on-disk write, that content is never returned inline, that captures include main-thread work and JS CPU samples, that screenshots roughly double file size, the duration defaults, the active-tab fallback, the WebKit zero-timestamp caveat, and the Web Inspector prerequisite.

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?

The description is long but appropriately so for a complex tool. It front-loads the core action and return shape, then logically covers file format, captured data, use case, parameter guidance, defaults, the timestamp caveat, and setup requirement. Every sentence carries operational information; there is no filler.

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?

There is no output schema, so the description supplies the return contract and also covers file size behavior, capture scope, the known WebKit timestamp failure, parameter defaults, and the required Web Inspector setting. The timestamped=false warning is exactly the kind of non-obvious context an agent cannot infer from schema alone.

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. The description adds meaningful context beyond the schema: url/triggerJs are the usual way to capture specific work rather than idle time, screenshots roughly double file size, and durationMs has a documented default/max in prose. It supplements rather than re-documents the schema.

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 opening sentence states a specific verb (Record), a specific resource (Safari page on an iOS device), a time window, and a concrete side effect (write to file on RDS host) with a return contract. The description also distinguishes this from general performance tools by scoping it to Safari/Web Inspector and explaining the file is a Chrome DevTools-loadable profile.

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 provides an explicit use case ('why is this page slow/janky') and concrete invocation patterns: pass url for page loads, triggerJs for interactions, set screenshots for a filmstrip. It does not name alternatives or state when not to use this tool, so it stops short of full when/when-not coverage.

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