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

Annotations only declare a safe read (readOnlyHint=true, openWorldHint=false), but the description adds meaningful behavior beyond that: the fixed count of 20, the exact returned fields, and the host-dependent UI rendering (interactive picker with tap-to-play previews). That rendering behavior is not derivable from any structured field.

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 what the tool returns, then the host-dependent response instructions. Every sentence earns its place, though the picker instruction is dense enough that it could be tightened slightly.

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 parameters and no output schema, the description fully carries the burden: it names the output fields, the count, and the crucial response-handling rule for UI vs non-UI hosts. An agent has everything needed to call it and respond 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?

The schema is empty with zero parameters, so there is nothing to document and the baseline of 4 applies. The description correctly implies the tool is a no-argument listing call, though it adds no parameter detail (none exists to add).

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 precise verb+resource with scope ('the 20 ElevenLabs Eleven v3 voices available for create_voiceover') and lists the returned fields, so it is immediately distinguishable from the sibling list_voices and tied to its consumer create_voiceover.

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 explicit conditional guidance: in app-capable hosts use the picker and do NOT repeat the voices as a table/list/summary; only in hosts without the UI share preview URLs. This is exactly the when/how-to-present routing an agent needs and leaves nothing to inference.

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