auto_analyze_audio

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

With no annotations provided, the description carries full responsibility for disclosing behavioral traits. It clearly states the synchronous nature and absence of job_id, and enumerates the specific return values (peak level, noise floor, duration, clipping status, recommendation). It omits explicit confirmation that the tool is non-destructive, though this is implied by the analysis context.

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 consists of five sentences with zero waste, front-loading the core purpose before detailing operational characteristics (synchronicity) and return values. The use of capitalization for 'SYNCHRONOUS' and 'IMPORTANT' effectively highlights critical operational constraints without adding verbosity.

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?

Given the absence of an output schema and annotations, the description comprehensively compensates by listing all returned analysis metrics (peak level, noise floor, duration, clipping status, pipeline recommendation). It also establishes the operational context (Audacity audio loading requirement) and relationship to the broader auto_* pipeline ecosystem.

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?

The input schema contains zero parameters, establishing a baseline score of 4. The description adds critical semantic context about the implicit input by specifying 'current audio track' and the prerequisite to load audio into Audacity first, effectively documenting the required application state.

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 opens with the specific verb 'Analyze' paired with the resource 'current audio track' and the outcome 'recommend the best pipeline to use.' It distinguishes itself from sibling analyze tools (analyze_beat_finder, analyze_contrast) by emphasizing the pipeline recommendation aspect, and from the auto_* pipelines by being the prerequisite analysis step rather than the processing itself.

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 explicit prerequisites with 'IMPORTANT: Load your audio into Audacity before calling this.' It distinguishes synchronous behavior from asynchronous alternatives with 'This is SYNCHRONOUS — it returns the analysis directly, no job_id needed.' It guides users toward specific sibling tools by mentioning it recommends 'which auto_ pipeline to use next.'

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