analyze_audio_file

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: loudness measures the source stream, channel selection applies only to optional analyses, and it requires external tools (ffmpeg/ffprobe). It also clarifies that pitch measurement is not pitch correction, adding transparency beyond the schema.

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 description is three concise sentences with no redundancy. It front-loads the primary purpose, then clarifies scope, exclusions, and prerequisites. Every sentence adds necessary information without filler.

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 tool with 11 parameters and multiple optional analyses, the description provides adequate context: it states what it measures, what is optional, exclusions, and external requirements. It does not describe the return format, but the lack of an output schema makes this less critical; the description's clarity about the measurements implies the output. It is reasonably complete for an agent 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 100%, so each parameter is documented. The description adds valuable semantic clarification: 'Loudness measures the source stream; channel selection applies to optional analyses' clarifies how channelIndex behaves, and 'Not Live processing or pitch correction' clarifies the intent of targetMidiNote. This goes beyond the schema's basic field descriptions.

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 clearly states the tool measures local source audio loudness, true peak, format, and optional spectral analyses, with a specific verb and resource. It differentiates from sibling tools like analyze_audio_clip by explicitly stating 'local source audio' and 'Not Live processing,' making its scope distinct.

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 provides clear context on when to use the tool: for local source files requiring ffmpeg/ffprobe, and explicitly excludes Live processing and pitch correction. However, it does not name alternative tools (e.g., analyze_audio_clip) or specify when not to use it beyond these exclusions, leaving some inference to the agent.

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