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

Carries the full burden of behavior well beyond annotations: 100-character limit causing HTTP 400, credit hold-and-refund semantics, async job contract ({id, status} then poll getApiJob), and request_id dedupe behavior. The only gap is that it defers the job/credit contract to server instructions rather than restating it, which is acceptable given the pointer. Note the annotation idempotentHint=false is not contradicted — keyed dedupe via request_id is a narrower guarantee.

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 primary action, then constraints, then sibling routing, then async/credit notes — a sensible priority order. It runs long and packs the credit line separately, but nearly every sentence adds information; only the credits sentence is mildly redundant with the held/refunded statement earlier.

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 compensates fully: it describes the returned audio result, the URL and MP3/WAV extension convention, the async polling path, and the credit lifecycle. Nothing an agent needs to call this correctly or interpret the result 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 baseline is 3. The description does add a little beyond the schema: the conditional requirement (text plus voice_description or image), the type enum's human/non-human meaning, and the consequence of exceeding 100 characters. But the field-by-field detail (augment_prompt, request_id, image size limits) is already fully documented in the schema, so no credit above baseline.

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 ('Design a new voice from a character description... or image') plus the concrete outcome ('have it speak a short line of text, returning a sample'). It also names the two nearest siblings (createSpeech, createSpeechPreset) and the exact axis that separates them, so an agent can disambiguate 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?

Explicitly says 'Use this to invent and audition a voice from a description', then gives when-to-use-otherwise: createSpeech for cloning from an audio sample, createSpeechPreset for named presets. The image-vs-description tradeoff is also spelled out, which is the main routing decision inside the tool.

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