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

Annotations declare the safety profile (non-read-only, non-idempotent, non-destructive), and the description adds substantial behavior: each cut edge lands audio-safe on the source's sound, moves report in the result, and running-speech joins are flagged. It does not cover failure modes (e.g., out-of-range times, project mismatch) or rate/permission constraints, so it is strong but not exhaustive.

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-loads the PROJECT-SCOPED constraint and the core action, and every sentence carries content. However, it is a dense wall of clause-heavy prose (the audio-safe sentence packs several nested conditions) that could be split for faster parsing.

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 compensates by stating that the result reports every move and any cut joining running speech. Combined with the scope constraint, snapping behavior, and sibling routing, an agent has everything needed to call it correctly.

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 25% (project_id alone documented), so the description must compensate and does: start/end are SOURCE seconds of the main video only, and snap_to_words is defined bidirectionally (true = move edges outward to word edges with a breath; false = keep exact times, a stutter cut). This is meaning well beyond the bare number/boolean types.

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 — 'Remove ONE source-time range from the current keep set' — plus the side effect ('Creates a new EDL version') and the scope ('a local edit'). It explicitly distinguishes itself from the sibling cut_output_range, so an agent can route 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?

Gives an explicit when-to-use rule ('SOURCE seconds of the main video ONLY') and a concrete when-not with the alternative named: if the user gives times of the edited video or the span sits inside an inserted clip, use cut_output_range. It even supplies a sample utterance ('cut 12-15 of the video') to disambiguate.

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