analyze_audio

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

With no annotations, the description carries the full burden, and it does well: it discloses supported formats (WAV/AIFF/FLAC), the full metric set, and interpretation thresholds (fireplace ~25-30 dB, crackle_ratio >= 4, hum > 3x local median). It omits that the operation is read-only/non-destructive and gives no performance or failure behavior, so not a full 5.

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?

Front-loaded with the core purpose in the opening clause, then a dense but earnable list of metrics and their interpretive thresholds. It is long and abbreviation-heavy (p95-p10, p99/median), but nearly every clause adds discriminative value.

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?

No output schema exists, so the description must describe the return values, and it does so comprehensively, including metric semantics and how to read them. The main gap is the unexplained section_seconds parameter and the absence of any note on cost/behavior for large files.

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%, so the description must compensate. 'path' is self-evident, but 'section_seconds' is never explained — the phrase 'loudness per section' only indirectly implies it, with no units, default-null behavior, or effect on output documented.

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 ('analyze a WAV/AIFF/FLAC') and enumerates exactly what it measures (LUFS, peaks, crest factor, correlation, texture). The detail is enough to tell it apart from a plain level meter, but it never names or contrasts the closest sibling (measure_levels), so sibling differentiation is left implicit.

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 'texture' block is framed for Foley/ambiences and the tonal_peak note ('on music it is just a note, so ignore it there') guides context. However, there is no explicit when-to-use, when-not-to-use, or routing to alternatives such as measure_levels.

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