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

Annotations already declare the safety profile (readOnly=false, destructive=false, openWorld=false), so the bar is lower, and the description adds a genuinely non-obvious trait: processing is 'applied on export,' meaning the change is deferred rather than rendered immediately. It does not disclose what happens when both flags are false, whether omitted flags preserve prior settings, or any permission/response behavior.

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?

A single front-loaded sentence with the export-timing caveat placed early and no filler. The parenthetical effect list is dense but readable; slightly awkward as one long clause rather than two, which keeps it from a 5.

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 4-parameter mutation tool with no output schema, the definition covers purpose and flag semantics but omits how multiple clip IDs are handled, what a false/omitted flag does, and what the result of the call is. It is workable but leaves meaningful gaps an agent would have to probe.

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 only 25% (just projectId documented), so the description has to compensate, and it does for the two ambiguous booleans by explaining what each audibly does. clipIds is left unexplained and the interaction between denoise and enhance is not described, keeping it short of a 5.

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?

The description gives a specific verb and resource ('Clean up voice on clips') and then defines each of the two feature flags, distinguishing denoise (hiss/room noise removal) from enhance (low-cut, presence EQ, compression). This lets an agent understand the operation without opening the schema, though it never names or contrasts the nearest siblings such as level_audio or voice_captions.

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 implied rather than stated: the description makes clear this is for voice cleanup on clips and that it applies at export, but it gives no explicit when-to-use/when-not conditions and no routing to alternatives like level_audio for loudness or remove_silences for gaps. An agent must infer the choice from the verb alone.

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