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

Adds substantial context beyond the annotations: credit cost per video (including unavailable captions), refunds on processing failure, and return of a jobId. The annotations already declare destructiveHint=true and idempotentHint=false, so the description's job is to explain the cost/refund model, which it does well. It stops short of stating whether resubmitting the same links double-charges, which would complete the behavioral picture.

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, front-loaded with the action, then the cost model, then the return value and polling guidance. Every sentence earns its place.

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 an async, credit-consuming mutation with no output schema, the description covers the essential return contract (jobId) and polling path. It leaves a minor gap on parameter behavior (maxVideos/links credit interaction), so not fully complete but adequate for correct invocation.

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 50%: language and fallbackToOriginal are documented in-schema, but links and maxVideos are not, and the description does not compensate for them. The description adds no parameter-level meaning (e.g., credit implications of maxVideos), so it sits at the baseline for a partially-covered schema.

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 ('Start an asynchronous transcription job') and immediately distinguishes itself from the polling sibling get_transcription. An agent can tell exactly what this tool initiates versus what get_transcription does.

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?

Explicitly routes the agent: 'poll get_transcription instead of submitting again.' This names the alternative and the condition (after submission, use the getter) rather than leaving it to inference.

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