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

Annotations are sparse (readOnlyHint:false, openWorldHint:true) so the description carries most of the burden. It discloses two important behaviors: per-file cost and asynchronous execution with polling. It doesn't mention failure modes or result format, but the async pattern is the most critical trait and is clearly stated.

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 with no filler: the purpose is the first sentence, then cost and async flow. Every sentence adds unique information and the most critical detail (async) is front-loaded after the purpose.

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?

The tool has only 3 parameters and no output schema, yet the description covers the main operational need: how to handle the asynchronous response. It doesn't describe the final transcript content (whether it's in the generation result), but that is likely handled by get_generation, and the polling instruction is sufficient for an agent to proceed.

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% – each parameter (audio, language, translate) already has a description and language has an enum. The description adds no extra detail about parameter formats, defaults, or edge cases, so it doesn't elevate beyond the schema baseline of 3.

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 opens with 'Transcribe audio to text', a specific verb+resource that clearly states the tool's function. It distinguishes itself from the many image/video siblings and from ai_audio_translator by using the word 'transcribe' rather than 'translate', so an agent can select it correctly even without opening the schema.

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 explains the asynchronous workflow (returns generation_id, poll get_generation) and the cost, which is useful for when to invoke it. However, it never names alternatives or states when not to use it, such as 'use ai_audio_translator for translation' – so the agent must infer the scope from the purpose alone.

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