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

Goes well beyond the annotations (which only mark it non-read-only, non-idempotent, non-destructive) by disclosing character caps per voice family, automatic queuing instead of erroring, character-per-minute fair-use pacing, the up-to-20-second wait, and the exact error semantics when the wait would exceed that. It also states the return shape (hosted URL, no inline audio), which is real operational context.

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-loads the purpose in the first clause and then layers constraints in descending importance. It is dense but every clause carries operational meaning; the em-dash chain of limits makes it slightly harder to scan than a bulleted breakdown would be.

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 generation tool with an output schema, the description covers everything the caller needs: entitlement gating, per-voice length limits, overflow behavior, throttling, and failure mode. Nothing required to invoke it correctly 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 50% — `text` and `voice` are documented in-schema while `speed` and `format` are not. The description compensates by explaining the voice id families (catalog vs. voice_* clones), Arabic ar_* limits, and MP3/WAV output, but `speed` is never mentioned in either place, leaving one parameter fully unexplained.

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?

Specific verb + resource (convert text to MP3/WAV audio) plus the scope of voices available (66 neural voices or cloned voice_* ids). It clearly distinguishes itself from siblings like list_voices and get_job_status by naming the polling path for overflow jobs, so an agent can tell what this tool does 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?

Explicit about eligibility (Pro or active 7-day pass; English) and about the free-tier voice subset, plus a concrete fallback instruction to poll get_job_status with the returned job_id when text exceeds limits. The one gap is that it never contrasts itself with generate_long_form, the obvious sibling for long inputs, leaving the agent to infer which one to use for large text.

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