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

Goes well beyond the annotations by disclosing the full job lifecycle: the server pulls the file from download_url, parks it in Cloudflare R2, processes it via the ihateaudio.com tool page in a headless browser, deletes the input when the job ends, and returns download links that expire after 1 hour. These are exactly the traits (temporary storage, output expiry, deletion) an agent needs and that no annotation conveys.

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-loads the purpose, then inputs, then outputs, then infrastructure in a compact paragraph with no filler. The final sentence on R2/headless-browser internals is the longest and least actionable, keeping it just short of a 5.

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 mutation tool with no output schema, the description covers the return value (expiring download links), input source, and cleanup behavior, which is nearly everything needed. The only remaining gap is the unresolved one-file-vs-twelve-files inconsistency with the schema's maxItems.

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 the baseline is 3, but the description adds real meaning: it names the settings sub-keys (preset, semitones), gives concrete outputFormat examples (mp3, wav, m4a), and scopes bitrateKbps to lossy formats 'where the tool supports them.' It slightly conflicts with the schema's maxItems of 12 by saying 'Input: one file.'

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 and resource ('Applies a voice effect preset or a pitch shift to a recorded voice'), which is far more informative than the title alone. It does not, however, name the closest siblings (pitch_shifter, nightcore_maker, slowed_reverb) or explain how the voice-effect preset differs from a plain pitch shift, so an agent must still infer the boundary.

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?

Gives practical context (one input file with a public HTTPS download_url, optional settings/outputFormat/bitrateKbps 'where the tool supports them'), which implies how to call it. It never says when to choose this over pitch_shifter or speed_changer, and offers no exclusions, so usage is only implied.

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