Refine a draft voice

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

Annotations only declare non-readonly, non-destructive, non-idempotent; the description adds the material behavior: every call mints a new draft handle while prior handles retain their versions, saved voices are never altered, and each call costs 5 credits with retries charged again. That credit/versioning disclosure is exactly what an agent needs to avoid surprise costs or lost work.

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?

Front-loaded with the core action, then the instruction semantics, then versioning, then alternatives and cost. Every sentence carries distinct information, but the closing sentence is dense enough that it reads as two obligations (cost plus retry billing) compressed into one, and the sibling differentiation slightly overlaps with usage guidance.

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?

With no output schema, the description correctly fills the gap by stating the return value ('a new draft handle') and the state model across calls. For a 3-parameter, non-idempotent, billed mutation, nothing an agent needs in order to call it correctly and safely is missing.

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; the description earns above it by explaining what 'instruction' means in practice ('a little lower and slower', 'warmer, and older') and constraining it to a single quality change. The 'play its new line' phrasing also gives context for the play flag, though it doesn't restate the default or the file-saving behavior.

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 ('Change a draft voice in words and play its new line') and immediately distinguishes it from design_voice, save_voice, and rename_voice. An agent can tell this is the iterative-refinement step rather than the create/save/rename steps without opening any 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?

Gives explicit when-to-use semantics ('change one quality at a time', with example instructions) and explicit routing to alternatives: save_voice keeps the draft the user picks, rename_voice only changes a name, and refining never mutates a saved voice. Exclusions and handoffs are both named.

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