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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real value with cost ('Free'), latency ('a long file takes up to a few minutes'), method ('read by ffmpeg'), and a shared-project access note. It does not describe the shape of the returned data (per-cut timestamps, span boundaries), which matters since there is no output 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?

Purpose is front-loaded and every clause carries information — no filler. It is dense with comma-spliced clauses and parentheticals, which slows reading, but nothing is redundant.

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 does explain the two return kinds (cut timestamps and still spans) and adds cost/latency so an agent can plan. It stops short of specifying result formatting or how project_id resolves media, so an agent still has gaps on what the payload looks like.

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% and each parameter is documented in-schema (media_id vs media_name alternative, threshold 0.1–0.9 with default 0.4). The description adds no parameter-level meaning beyond that, so the baseline 3 would apply — but the front-loaded mention of what a 'cut' is implicitly frames threshold semantics in the body text, edging it slightly above baseline.

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 ('Find the scene changes in a video of your Editor project') plus the concrete output ('the seconds in the file where the picture cuts, read by ffmpeg'), and adds the secondary output (stills/spans where the picture holds still). Scope is bounded to Editor projects including shared ones, which separates it from generic video tools like analyze_video.

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?

Names the exact consumers and the condition for each: edit_editor_timeline split_scenes to cut a placed clip, auto_clip to lay pieces in a row. It also gives a hard rule of practice — 'cut inside a still span, never mid swipe or mid scroll' — which is when-and-how guidance beyond simple routing.

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