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

Goes well past the annotations by disclosing the billing model (USD 0.01 per call, failed calls free), the practical consequence that retries are not free, and the exact return encoding (MP3 base64). That pricing detail also explains behaviorally why idempotentHint is false, which the annotation alone does not convey.

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 capability, then use cases, then example, then cost — a sensible order with little wasted text. Minor redundancy: 'Reads or computes only and changes nothing' repeats readOnlyHint/destructiveHint, and the voice counts partially duplicate the enum listing.

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 still specifies the output shape (MP3 base64), the length limit, language/voice choice and defaults, and the cost model — everything needed to call it correctly and predict the result.

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 100%, including the full voice enum list and defaults, so the schema already carries most parameter meaning. The description adds only light framing: 40 English and 10 Spanish voices and 'pick a voice by name or keep the default,' which restates rather than extends the 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?

Names a specific verb and resource (text to speech, text into MP3 base64 audio), the provider and model family (Deepgram Aura-2), the supported languages and voice counts, and the 300-character cap. An agent knows exactly what it gets back 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?

Concrete use cases are listed (voice replies, narration, audio notes, IVR prompts, accessibility) plus a worked example call. It stops short of naming when NOT to use it or routing away from a sibling (e.g. ai_speech, transcribe), so the boundary with the rest of the ai_* family is left implicit.

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