transcribe

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

Annotations already declare readOnly=true, idempotent=true, and destructive=false, which the description reinforces without contradicting. The description adds valuable behavioral context beyond annotations: the billing model (x402, $0.030/call), file size and duration caps, and the fact that no API key is required. This is helpful, though it doesn't elaborate on error handling or response format (covered by output 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?

The description is compact and front-loads the most critical operational info (cost, wallet requirement) before the tool's core function. The limits and alternative variant are packed into a single sentence that earns its place. It's slightly dense but still easy to parse. No wasted words.

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 simple transcribe tool with only two parameters (one required) and an output schema, the description covers the essentials: purpose, cost, auth model, limits, and the alternative for longer audio. The only missing nuance is explicit mention of the return format, but that is presumably described in the output schema. Overall, an agent has everything needed to call it correctly.

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 schema already documents both parameters (url and language). The description adds a small extra semantic detail ('for better accuracy' about the language parameter) but doesn't materially enrich parameter understanding beyond what the schema provides. Baseline 3 is appropriate.

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?

The description clearly states the verb (transcribe), the resource (audio), and the output (transcript). It explicitly names the underlying model (gpt-transcribe) and lists supported formats. This is unambiguous and distinguishes it from any other tool in the sibling list, none of which perform transcription.

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 provides explicit usage context: cost per call, wallet requirement, no API key needed, and hard limits (4 minutes, 25 MB). It also points to an alternative endpoint (transcribe-pro) for longer audio, effectively guiding the agent on when to use this tool vs. the other variant. This is exactly the kind of when-to-use guidance needed.

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