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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds substantial context: ownership/checksum constraints, the exact measurement set, preview audio return behavior, and explicit limitations. No contradiction with annotations.

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 sentences with no filler: the first front-loads the core action, resource, and measurement list; the second compactly covers preview behavior and non-goals. Every sentence 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?

Covers purpose, measurements, preview behavior, and non-goals despite having no output schema. The main gaps are the undocumented previewOffsetSeconds parameter and lack of return-structure detail, but for a read-only inspection tool with strong annotations this is nearly complete.

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 only 33%, so the description must compensate. It clarifies previewSeconds ('returns up to three seconds as playable MCP audio') but leaves previewOffsetSeconds entirely unexplained in both the schema and the description, leaving a meaningful parameter without semantic guidance.

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 ('Measure') and resource ('checksum-verified owned PCM16 WAV'), then enumerates concrete metrics such as peak/RMS/DC, clipped samples, and loop-boundary differences. It also explicitly contrasts with non-goals ('does not listen, judge sound quality, measure LUFS or certify a seamless loop'), making it clearly distinguishable from siblings like audio_generate and artifact_get.

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?

Provides clear context: this tool is for measuring sample-level properties without Blender compute, and it explicitly lists exclusions such as not judging sound quality or measuring LUFS. However, it does not name a specific sibling tool to use instead, so the guidance is strong but not fully explicit.

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