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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds real domain knowledge beyond that: standard voices cost zero, premium voices consume at most one premium character per character, and "value voices" consume less, plus the call itself is free. The only gap is what the response shape actually looks like.

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?

Four short sentences, front-loaded with the core question and followed by the cost rule and input guidance; no filler. Minor deduction for the garbled fragment "(value voices less)", which is the one place a reader has to guess at meaning.

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 and a numeric result, the description should state that the return is a character count (and whether it is a single number or totals per voice/category). It conveys the cost model but leaves the return value unstated, so the agent knows what to send but not exactly what it will receive.

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 all three parameters are already documented, and the description's "Give the text, or just its length in characters" largely restates what the schema says for text/characters. It says nothing extra about the required voice parameter beyond the schema's pointer to list_voices, so the baseline of 3 is appropriate.

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?

"How many premium characters a text would use with a voice, without making audio" names the specific computation (premium character cost) and the resource (text + voice), and the phrase "without making audio" cleanly separates it from the sibling text_to_speech. An agent can distinguish this estimator from the generation tools without opening a 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?

The description implies usage ("Free to call", "without making audio") suggesting it is a cheap pre-check before invoking text_to_speech or create_speech_job, but it never states that explicitly or names an alternative. It does explain the two input modes (text or character count), which is more parameter guidance than when-to-use guidance.

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