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

Beyond annotations (which only cover readOnly/idempotent/destructive/openWorld), it discloses credit expenditure, the two-step estimate-then-confirm flow, and the cloned-voice consent requirement — exactly the operational context annotations cannot express.

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 purpose, then the cost/quote flow, then the consent caveat. Dense but every sentence carries information; the phrasing 'a voice that cannot be priced ahead cannot be made here' is slightly convoluted but 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?

No output schema exists, and the description covers the key outputs (a job, credits spent, linked audio) plus prerequisites (saved voice, consent). It could mention polling via get_job/wait_job, but the agent has enough to invoke and interpret results 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 coverage is 100%, so the baseline would be 3, but the description adds real meaning to the 'quote' parameter (its presence vs absence changes the call's behavior entirely) and clarifies the text vs script alternatives, which the schema does not.

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 states a specific verb + resource ('Speaks a line or a saved script in a saved voice') and states the return ('a job whose result links the audio'), which cleanly separates it from sibling generation tools like make_video or write_script.

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 gives concrete procedural guidance: call without a quote to get cost, then re-issue with the quote after the person confirms, and warns that unpricable voices cannot be made here. It doesn't route to sibling tools, but the when/how guidance is unusually explicit.

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