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

Beyond the annotations, it discloses the commercial model ($0.05 USDC on Base, per call), the exact payment protocol (x402, payment passed in _meta['x402/payment']), and the failure mode when payment is absent (returns payment requirements). That is precisely the behavioral context an agent needs to invoke a paid endpoint without a failed call.

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?

Two sentences, front-loaded with capability and limits, with the payment mechanics last. It is dense but every clause carries actionable information; the payment sentence is somewhat packed with parenthetical detail, which costs it a point.

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?

There is no output schema, so the description compensates by naming the return payload (text, timed segments, SRT file). Combined with input constraints, format list, and payment semantics, an agent has everything needed to call it correctly and anticipate the response.

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: language is optional and exists to skip auto-detection, and audio_url is a public https link accepted across mp3/wav/m4a/ogg/webm/mp4 (the schema does list formats, but the 'auto-detected by default' framing clarifies the default path).

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 explicit scope (15 minutes, 20 MB, any auto-detected language) and enumerates the input types it handles. It does not, however, distinguish itself from the sibling vngrd_subtitles, which an agent could reasonably confuse with a transcript-plus-SRT tool.

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 context for when to reach for it (podcast, interview, voice note, live set, video soundtrack) along with hard limits that determine eligibility. It stops short of naming when *not* to use it or routing to the sibling subtitle/voice tools, so selection between overlapping siblings still requires inference.

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