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

Annotations only say it is a non-read-only, non-destructive, non-idempotent write; the description adds the credit model ('characters x voice rate'), the async contract, and the returned fields (job_id, status, audio_url). It does not state failure/retry behavior or permission requirements, which keeps it short of a 5.

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?

Three sentences, front-loaded with the core conversion, then usage, then cost/return. Every sentence carries distinct information with no repetition of the tool name or title.

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, describing job_id/status/audio_url is genuinely necessary and present, and the wait_seconds/PENDING handoff is covered in the schema. Minor gap: no mention of what happens on provider failure or how long jobs persist.

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%, so the baseline is 3; the text restates text/voice cardinality but adds no syntax, format, or constraint detail beyond what the schema already carries (pitch provider caveat, wait_seconds PENDING flow).

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 concrete verb+resource with cardinality: 'Convert one text into one MP3 with one voice.' The 'one/one/one' framing implicitly distinguishes it from sibling tools like multi_voice_to_speech and srt_to_speech without needing 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?

Gives a clear positive-use context (narration, voiceover scripts, articles, lessons, announcements, 'any audio whose length can follow the speech'), which hints at what it is not for. It never names an explicit alternative such as multi_voice_to_speech or srt_to_speech, so routing is left partly to inference.

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