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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds substantial context beyond them: accepted formats, a 10 MB / 5 minute limit checked from the file itself, 24-hour content-addressed caching, and a 0.02 USDC cost with the x402 payment networks. This is exactly the operational detail an agent needs before calling a paid external service.

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?

Three sentences, front-loaded with the use case, then return contents, then limits/caching/cost. Every sentence carries distinct information with no 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?

With an output schema covering return values and annotations covering the safety profile, the description fills the remaining gaps: input constraints, caching behavior, and pricing. Nothing an agent needs to invoke it correctly 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 coverage is 100% for the single url parameter, so the baseline is 3. The description still adds value by specifying which audio formats and size/duration constraints the referenced file must satisfy, which constrains what a valid url argument looks like.

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 outcome (the words in an audio file) and a concrete resource, which implicitly separates it from text-extraction siblings like get_ocr or get_pdf_markdown. However, it never names an alternative explicitly, so an agent must infer the distinction from the 'audio file' scoping rather than being told.

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?

'Use when an agent needs the words in an audio file' gives clear selection context. It offers no when-not-to-use guidance or named alternatives (e.g., for images use get_ocr), so routing among the many text-extraction siblings is left to inference.

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