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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description goes well beyond them: it discloses that the server downloads the file, holds it in Cloudflare R2 for the job duration, processes it via a headless browser, returns JSON rather than a file, and deletes the input when the job ends. That data-lifecycle and retention detail is exactly the context an agent cannot get from 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?

Purpose and return type are front-loaded, and the infrastructure sentences are informative. Some implementation trivia (ihateaudio.com tool page, headless browser on Cloudflare) is heavier than the agent needs, but the overall length is justified by the data-handling disclosure.

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 tool with nested objects, no output schema, and a vague `settings` object, the description covers input requirements, processing pipeline, retention, and return type well. It stops short of describing the shape of the returned measurement JSON or what `settings` accepts, which would have closed the remaining gap.

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 the baseline is 3. The description restates the input shape ('one file with a public HTTPS download_url') and hints that the opaque `settings` object maps to 'set_analysis_range: selectionOnly', but that phrasing is cryptic and adds little actionable meaning for a free-form `additionalProperties: {}` object.

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+resource: 'Measures the tempo of a track in BPM.' The analysis verb cleanly separates it from transformation siblings like tempo_changer, speed_changer, or pitch_shifter, and 'Returns the measurements as JSON, not a file' reinforces that this is a read/measure operation rather than a file producer.

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?

The description implies the usage context (a measurement job over one audio file) and specifies input preconditions (public HTTPS download_url), but never states when to prefer this over key_finder, loudness_meter, or tempo_changer, nor any when-not conditions. Usage is inferable but not guided.

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