save_audio_style

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

With no annotations, the description must carry the behavioral burden. It discloses that this captures existing state and persists it as a default, but leaves open whether a prior default is overwritten, whether scope is per-project or global, and whether the operation is reversible.

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?

One sentence, zero filler, with the captured content front-loaded before the outcome. The trailing clause 'from a clip they set up by hand' is slightly awkward but earns its place by conveying the prerequisite.

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 one-parameter mutation with no annotations and no output schema, the description covers what is saved and why, but omits what 'ref' expects and what happens to an existing default. Those gaps are material for an agent invoking it unattended.

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% and the single parameter is named 'ref' with a default of '0' - a cryptic name the description never explains. 'From a clip' hints that ref identifies the source clip, but not whether it is an index, id, or timeline reference.

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 (Save) and resource (a clip's audio chain: volume, loudness/noise removal/EQ/effects) plus the outcome (becomes the user's default dialogue sound). This clearly separates it from apply_audio_style and apply_look, though it doesn't name those siblings explicitly.

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?

The phrase 'from a clip they set up by hand' implies the prerequisite that the source clip must already carry the desired chain, which is useful implicit guidance. It never states when to prefer this over save_look or apply_audio_style, nor any exclusion.

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