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

Annotations only declare readOnlyHint=true, and the description adds real behavioral context beyond that: the available=false flag means a voice must not be offered, and pricing is computed per line from estimated seconds (characters / charsPerSecond, minimum 1 s, multiplied by creditsPerSecond and versions). The remaining gaps (ordering, total count, language filtering) are minor for a read-only catalog call.

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?

The content is front-loaded and nearly every clause defines a returned field or a pricing term, so little is pure waste. However it is delivered as one long run-on sentence with mid-sentence glossary translations (homem = man, coloquial = loose), which makes it hard to scan; a short structured list of fields would carry the same information more efficiently.

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?

There is no output schema, so the description legitimately carries the burden of describing return values, and it does so thoroughly: per-voice id, name, person, style, localized description, registers, sample links, emotions, languages, maxChars and price. The pricing formula is dense and slightly ambiguous (what 'versions' multiplies), and the registers a voice actually offers versus the fixed enumerations is not fully distinguished, but an agent has enough to call and interpret it.

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?

The tool takes zero parameters and the schema coverage is 100%, so there is nothing to disambiguate on the input side. The description spends its words on output semantics instead, which is the right allocation.

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?

The opening clause 'The voice library for character lines (voice sounds)' plus the enumerated field list makes it clear this returns available voices and their attributes, which is distinct from the create/generate siblings. It stops short of a clean verb-first statement (e.g. 'Lists all voices'), so the agent infers 'list' from the title and field inventory rather than the description's lead.

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?

It gives two concrete usage rules: skip voices where available=false ('do not offer it') and feed the returned ids into create_voice. What it does not say is when to call this instead of the other discovery tools (choose_sound, find_sounds, generate_voice), or that it must be called before create_voice to obtain a valid voice id.

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