audio_process

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

Annotations only state non-readonly, non-destructive, closed-world. The description adds substantial context on top: input is never modified by default, the one override path (output==path with overwrite=true), default output path naming, and M4A/video inputs defaulting to WAV. It also discloses the return payload (before/after levels and warnings).

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?

The most safety-critical fact (a new file is written; input untouched) is front-loaded before the op catalog. The op listing is long but dense and non-redundant, since there is no structured documentation of the operations array elsewhere; minor tightening is possible but every line informs a caller.

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?

Despite no output schema and 0% schema coverage, the description covers defaults, format conversion, overwrite semantics, the full operation catalog, output subtype values, and the shape of the return value. An agent has everything needed to invoke this five-parameter tool 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 description coverage is 0%, so the description carries the full burden and does so well: it enumerates every operation name with its parameters and defaults (gain, normalize_*, denoise, fade, crop, resample, etc.), documents the operations object format with an example, explains output defaults, and lists valid subtype values like PCM_16/FLOAT/PCM_U8 for WAV.

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: 'Apply operations in order and write a NEW file', with concrete default naming and format-conversion behavior. It clearly conveys what the tool does, but it never names an alternative sibling (e.g. audio_batch_process for multi-file work), so an agent must infer the single-file vs batch split.

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: process one file with an ordered op list, and 'verify speech afterwards with audio_transcribe' hints at a follow-up step. There is no explicit when-to-use/when-not guidance or comparison to sibling tools like audio_batch_process or audio_analyze, leaving routing to inference.

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