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

Adds real context beyond annotations: synchronous ~3–15 s, CPU-bound, no credits, cancel not applicable because the response is the result, and the underlying method (basic-pitch) with its failure modes (dense chords, fast runs). Annotations already cover the read/write and open-world profile, so this is above bar, though it could state auth or size constraints more explicitly.

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 imperative and the payoff, with latency, cost, and method caveats deferred to the end. It is dense and long for a single paragraph, but nearly every clause carries information an agent needs.

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 fully compensates by describing the return payload (metrics, first missed notes with beats, timing error, loudness, verdict with reasons). Input alternatives, runtime, cost, and accuracy limits are all covered, leaving no material gap for correct invocation.

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 baseline is 3; the description earns extra by clarifying the input modes — notes[]+bpm/tempo_map versus midi_url — and that instrument names switch to onset-only matching. Defaults like onset_tolerance_ms and time_signature remain schema-only, which is fine given full coverage.

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?

Opens with a specific verb and resource ('MEASURE a take') and immediately enumerates what it returns (recall/precision/f1, octave errors, timing error, LUFS, verdict). The input requirements are stated inline, so an agent can tell this apart from siblings like doseedo_transcribe or doseedo_analyze_midi without opening the schema.

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?

Explicitly says when to use it and offers an alternative: doseedo_render_midi results already carry takes[].check, so checking a rendered part is redundant. It also gives the working caveat — 'use it as a screen, and listen to anything marked check' — which tells the agent how to act on the output.

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