measure_spectrum

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

Annotations only give readOnlyHint=true; the description adds real behavior beyond that: the measurement unit convention (dBFS, full-scale sine at 0, 'as in REAPER') and the external-analyzer dependency/install path. That dependency disclosure is exactly the kind of trait annotations cannot carry. It does not cover computational cost or failure behavior when the analyzer is absent, keeping it out of 5 territory.

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 metric list, then the two operational caveats (unit convention, install requirement) in terse sentences. Dense but each sentence earns its place; the enumerated metrics could arguably be trimmed but they substitute for a missing output schema.

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 usefully enumerates what gets returned and in what units, and it flags the external dependency — enough for an agent to call it correctly in the happy path. The remaining gap is scoping semantics: how the four un-documented parameters limit or target the measurement.

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 0% across four parameters (start_time, end_time, track_index, item_index), so the description must compensate and largely does not. 'Same targets and range as measure_loudness' is an indirect hint that the time/index parameters scope the measurement, but nothing states the meaning of track_index=-1, the time units, or how item_index interacts with track_index.

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?

Names a specific action ('Measure') plus the exact resource and the outputs: octave-band levels 31.5 Hz to 16 kHz, spectral centroid, tilt, stereo correlation, side-to-mid, L/R balance. An agent can distinguish it from measure_loudness and from analysis-adjacent siblings purely from the text.

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?

States a clear relationship to the sibling measure_loudness ('Same targets and range') and warns of a hard prerequisite (the TwelveTake MCP Analyzer, installed via --install-bridge), which is genuinely actionable. It stops short of explicit when-to-use/when-not guidance or naming the alternative to call for loudness-only needs.

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