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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false) by disclosing the full data path: server downloads from download_url, stores in Cloudflare R2 during the job, processes via a headless browser, deletes the input when the job ends, and returns download links that expire after 1 hour. These retention, storage, and expiry facts are exactly the context an agent needs and cannot get from the schema.

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: the first two sentences carry the core purpose and inputs, followed by output and infrastructure details. The Cloudflare/R2/headless-browser sentence is long but earns its place as behavioral disclosure rather than filler.

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 complex tool with a nested `files` array, an open-ended `settings` object, and no output schema, the description covers input constraints, the settings surface, return-value form and expiry, and the data-retention lifecycle. Nothing essential for correct invocation is missing.

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 does name the settings keys (method, parts, partLengthSec, silenceThresholdDbfs, minimumGapSec), but the schema's `settings` description already lists the same names, and the description adds no units, ranges, or valid values (e.g., dBFS thresholds or acceptable part counts). 'where the tool supports them' is vague for outputFormat/bitrateKbps.

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 ('Splits a recording into parts') and enumerates the three splitting modes (set number, set length, at silences), which is enough to distinguish it from nearby tools like audio_trimmer or silence_remover. It never names a sibling explicitly, so it falls short of the top score.

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 states a prerequisite ('one file with a public HTTPS download_url') and lists optional settings, but gives no explicit when-to-use vs. when-not-to-use guidance or alternative tools. Usage is implied rather than directed.

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