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

Goes well beyond the readOnly/idempotent/openWorld annotations: voices/models stay empty until a key is stored, credits/consent/hasApiKey gate premium use, download phases cannot be forced, and audio tags are spoken aloud on non-v3 models. These are exactly the behavioral traps an agent would otherwise hit.

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?

Front-loaded with the resource statement, but the body becomes a dense inline dump of nested return shapes with partial redundancy (the audio-tag rule restated by each model's `note`). Much of it earns its place as output-shape documentation, yet it could be tightened into a short list.

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, the description carries the entire burden of describing the return payload, and it does so comprehensively: provider arrays, voice fields, model capability flags, status object with credits and consent, plus per-state consequences. An agent can call this and interpret the result without further input.

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?

Only one parameter (token) at 100% schema coverage, and the schema already explains it is the session token from connect. Nothing further is needed, so the baseline applies.

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 description states the resource precisely: the text-to-speech providers the app can generate voiceovers with, and enumerates the returned provider shapes (free in-browser vs premium cloud). It clearly reads as a discovery/list tool, though it never names generate_voiceover directly, so the pairing must be inferred.

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 concrete usage conditions: read the top-level `elevenlabs` status before choosing the premium provider, and note that a provider in 'needs-download' cannot generate until enabled in the Generators panel. It also rules out an alternative ('there is no tool to force the download; ask the user'), which is strong guidance, but it stops short of explicitly directing the agent to call this before generate_voiceover.

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