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

With no annotations supplied, the description carries the full disclosure burden and does well: it names the model, the accepted formats, the 15 MB ceiling, and the paid x402 model with a concrete price of $0.01 USDC on Base. What it omits is failure behaviour (oversized or unreachable URLs), whether the call is synchronous or long-running, and any retry/refund semantics for a paid endpoint, which are meaningful gaps for a metered tool.

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 tight sentences that front-load the capability, then constraints, then cost, with no throat-clearing. The one redundant fragment is 'Optional language hint,' which only restates what the schema already declares.

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 two-parameter tool with no output schema and no annotations, the description covers everything an agent needs: input formats and size cap, the optional hint and its default, the exact return fields (transcript, detected language, duration, word count, timed segments), and the cost. Return shape is described precisely enough that the absence of an output schema is not a handicap.

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 both parameters are already documented in the schema, including the two-letter pattern and the 'detected when omitted' fallback. The description adds file-format and size constraints that bound what the url parameter may point at, but framing the language hint as just 'Optional' repeats the schema rather than extending it.

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 ('Speech to text with Whisper large-v3 turbo') and immediately explains the calling contract: pass an audio URL, get back a transcript. It is unmistakably distinct from its nearest sibling, ai_text_to_speech, because the direction of conversion and the input type (audio URL) are both explicit.

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 clear conditions for use: the input must be a publicly reachable audio file in MP3, WAV, OGG or M4A at up to 15 MB, and the language hint is optional because detection happens automatically. It does not name alternatives or state when not to use it, but no sibling does the same job, so the context is sufficient.

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