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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description adds behavior well beyond that: the call debits HanoLab credits, repeated calls with the same quote_id are idempotent and return the original task without a second debit, and a failed task blocks resubmission until the user makes a new decision. These are exactly the cost and retry semantics an agent needs.

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 dense sentences, front-loaded with the credit-spend precondition, each carrying distinct operational rules with no filler. It is slightly packed — the idempotency and failure rules are compressed — but 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 a 3-required-parameter mutation with no output schema, the description covers the critical unknowns: credit debiting, user confirmation gating, idempotent retry, and failure handling, and it incidentally reveals that a task is returned. Only the return payload shape and credit-ceiling behavior are left unspecified, which is acceptable given there is no output schema.

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 0%, so the description must carry parameter meaning. It gives real semantics for quote_id (must be reused exactly after interruption) and for max_credits/confirmed via the requirement that the user confirm cost and budget before submitting. It doesn't explain the 1-1000 max_credits bound or the uuid format, but the intent of each parameter is clear from prose.

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 names a specific action (submit the prepared conversion) and the resource (voice conversion), and it implicitly distinguishes itself from the sibling prepare_voice_conversion by requiring an existing quote_id and referring to 'the prepared conversion'. It stops short of naming the prepare tool explicitly, so an agent must infer the two-step relationship, but the purpose is unambiguous.

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?

It states explicit preconditions ('ONLY after the user confirms its cost and budget'), an idempotency rule for retries ('Reuse the exact quote_id after interruption'), and a recovery path for failures ('A failed task needs a separate user decision before a new quote'). When-to-use, when-not-to-retry, and the alternative action after failure are all spelled out.

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