update_style

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

With no annotations, the description carries the burden: it implies persistence ("saved style defaults") but never says whether changes apply retroactively to existing timelines, take effect on future edits only, or need a re-apply. The add_note behavior (storing a free-text preference) is a useful disclosure beyond the schema, but the operational impact is left implicit.

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?

Two sentences, front-loaded with the core action and then anchored by user-utterance examples. No filler; the parenthetical direction cues ("raise", "lower") earn their place.

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?

A 7-parameter mutation tool with no annotations and no output schema needs more than this: four parameters are unexplained and there is no statement about persistence scope, defaults, or what happens to omitted fields. What is present is good, but the coverage gap is large.

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 0%, so the description must compensate for all seven params, and it explains only three: keep_after_speech, min_silence, and add_note. threshold_db, default_look, remove_stutters, and keep_before_speech get no meaning at all, leaving over half the surface undocumented anywhere.

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?

"Change saved style defaults" is a specific verb+resource that clearly separates this tool from timeline-editing siblings like cut_ranges or trim_clip. It doesn't explicitly distinguish itself from get_style or save_audio_style, but the notion of per-editor defaults is unambiguous.

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?

It gives concrete trigger language ("when the user says cuts feel too tight… or too loose") and maps each to the right knob, which is exactly the routing an agent needs. It stops short of saying when to prefer this over apply_audio_style or when not to call it.

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