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 reasonably well: it discloses the caching side effect (results written next to the project) and a concrete failure mode (essentia_unavailable in builds lacking Essentia). It stops short of stating cost, duration, or whether re-analysis overwrites the cache.

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?

Two tight sentences with no filler, and the core purpose plus target is front-loaded before the failure-mode caveat. Slightly dense but every clause earns its place.

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 2-parameter, no-output-schema tool, the definition covers target scope, produced data, caching behavior, and a build-dependent failure mode. Only the exact return shape and re-run semantics are unstated, which is minor here.

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 100%, so both target and types are already documented in the schema, including the default merge set. The description adds only indirect meaning by naming the categories of analysis (segment boundaries, beats, BPM) that map to the types parameter. Baseline 3 is appropriate.

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?

It names a specific verb (analyze) and the concrete outputs (segment boundaries, beats, BPM) via a named engine, and it explicitly scopes the target to the project's audio files or a standalone file. That distinguishes it from downstream consumers like auto_edit/assemble and from import/export audio tools.

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: caching results 'for auto_edit/assemble to use' hints that this precedes editing, but there is no explicit when-to-run/when-not guidance or named alternative. The agent must infer the workflow position.

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