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

Annotations already declare readOnlyHint, openWorldHint=false, and destructiveHint=false, and the description reinforces 'Free and read only.' It adds genuine behavioral context: the return fields (voice_id, name, type, labels, preview_url), how search matches names/descriptions, that count defaults to 30 with max 100, and that mine_only includes reference voices.

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 purpose is front-loaded, and the dense paragraph is organized around what is returned, then filters, then defaults, then safety. Every sentence carries useful information with no filler.

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, but the description fully covers the return shape and the meaning of each field. All three parameters are explained, and the read-only, free behavior is stated. An agent has everything needed to call this correctly.

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 the baseline is 3. The description adds value beyond the schema by giving semantic examples for search ('warm female narrator', 'deep british male') and clarifying that mine_only includes reference voices matched from a clip.

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 specific verb and resource: lists voices available to speak with, and enumerates exactly which voices are included (library plus cloned/designed). It clearly distinguishes itself from siblings like clone_voice, design_voice, or delete_voice, which imply mutation.

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?

Makes the primary use case clear: find a voice_id to pass to speaking tools. It explains the optional search and mine_only filters with examples. It doesn't explicitly name alternatives for creating voices, but the listing purpose is unambiguous.

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