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 does well: it declares the side effect (reads the file from disk), and specifies the failure contract — missing files and unsupported encodings return a structured {"ok": False, "reason": ...}. It omits anything about cost, latency, or supported formats, which is the remaining gap.

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?

Tightly structured with front-loaded purpose, then labelled Side effects, Example, and Edge cases blocks. Every sentence adds information an agent needs; no 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?

With no output schema, the description must describe the return value, and it does list the metrics returned (LUFS-I, true-peak, RMS, per-band energy) plus the error shape. It stops short of describing result structure or units, so a little is left to discovery, but nothing critical is missing for a 1-parameter read tool.

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% and the single parameter is undocumented in the schema, so the description must compensate — and it does via the worked example path="/stems/kick.wav", which conveys that path is a local filesystem path string. Absolute-vs-relative and platform conventions are still left to inference.

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 (compute) and resource (a local audio file) plus the exact metrics produced: LUFS-I, true-peak, RMS, and per-band energy. This is far more specific than its sibling analysis tools (analyze_mix, find_frequency_masking), though it never explicitly names how it differs from them.

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: the metric list tells the agent this is for objective loudness/level measurement of a single file, and the example demonstrates the call shape. However, there is no statement of when to prefer this over analyze_mix or find_frequency_masking, and no preconditions are described.

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