frames

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

Annotations only carry the generic safety profile, and the description adds substantial behavioral context: it refuses on hidden pages because rAF/observers stop, synthetic events yield no interaction id, compositor-only animations can stay smooth while the main thread drops frames, and an action can run right after recording starts. These are genuine operational traits not visible in structured fields.

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 core purpose and tightly information-dense, with no filler sentences. It is long and parenthetical-heavy (render/style layout start, CLS/INP window caveats), which slightly taxes readability, but nearly every clause carries real meaning.

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 a 6-parameter tool with a nested action object and no output schema, the description fully explains the returned metrics (frame rate, dropped frames, LoAF details, shifts with moved elements, INP split into input delay/processing/presentation) plus the hidden-page and trusted-input constraints. Nothing essential is missing.

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%, so all six parameters (limit, action, tab_id, frame_id, duration_ms, threshold_ms) are already documented. The description adds the action types (click, hover, scroll, key) and the trusted-input requirement, but this only marginally extends what the schema already provides; baseline 3 is appropriate.

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 (record) and resource (the page/frame performance window) and enumerates exactly what it reports: frame rate, dropped frames, LoAF, layout shifts, INP. An agent can distinguish this from perf_trace, lighthouse, and animations without opening a schema.

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?

Implied usage is clear from the metric set (use it to measure smoothness/interaction responsiveness over a window), and it notes constraints like needing trusted input for INP. But it never names an alternative (perf_trace, lighthouse, animations) or states when this is preferred over them.

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