record_site_motion

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the description's job is to add behavior beyond the safety profile — and it does: inline filmstrip JPEG plus a .webm path, an additional on-disk Motion Evidence Sheet (keyframes, diff masks, cursor-trail overlay, timeline strip), and the optional playwright/ffmpeg-static dependency requirement. What it omits is failure behavior when those optional deps are absent and any runtime/duration limits on 'short' recording.

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 and output before the dependency and side-artifact details. The parenthetical inventories (preloader/scroll/hover; keyframes/diff masks/cursor-trail/timeline) are dense but each clause carries distinct information, so little is 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 — inline filmstrip JPEG, .webm path, and the evidence sheet are all named. Parameters are covered by the schema and the environment prerequisite is disclosed; only error/edge behavior (missing optional deps, very heavy sites, recording time bounds) is left unstated.

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% and all four parameters (url, frames, viewport, waitStrategy) are documented with defaults, ranges, and enum meanings in the schema itself. The description adds nothing parameter-specific — it names only the target ('live website') — so the baseline 3 for schema-carried parameter semantics is correct.

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 precise verb+resource ('Record a short motion-through video of a live website') and enumerates exactly what motion is captured (preloader, scroll-triggered, hover/cursor) plus the concrete outputs (inline filmstrip JPEG, .webm path, Motion Evidence Sheet). It is very clear what the tool does, but it never names or contrasts itself with the nearby siblings (capture_live_site, analyze_hover_census, analyze_scroll_map, get_motion_dna), so the agent must infer the boundary itself.

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?

Usage is only implied by what gets captured — there is no explicit when-to-use, when-not-to-use, or alternative-naming guidance, which matters given several sibling tools cover overlapping motion/scroll/hover analysis. The dependency prerequisite ('Requires the optional playwright and ffmpeg-static dependencies') is a useful precondition but does not tell the agent when to pick this over capture_live_site.

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