generate a speech preview

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

Annotations declare destructiveHint=true and idempotentHint=false, and the description justifies both by calling this a 'potentially paid action' whose only deduplication is the supplied idempotencyKey. It additionally discloses the return lifecycle (PENDING/PROCESSING/SUCCESS/FAILED, url and duration only on SUCCESS) and pre-synthesis failures. It does not contradict the annotations — a new key can bill again, which is consistent with idempotentHint=false — but it could have been a touch more explicit about the billing trigger.

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 and the paid-action warning are front-loaded, and nearly every sentence carries an operational rule. It is a single dense paragraph, though, and the polling/retry/anti-duplicate rules would scan faster as discrete lines; a few clauses restate the schema descriptions for projectId and idempotencyKey.

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?

For a paid, open-world, job-creating mutation with seven parameters and an output schema, the definition covers selection, prerequisites, side effects, failure modes, polling, retry semantics and sibling routing. Nothing an agent needs in order to call it safely is missing, and the return-shape note is a bonus rather than filler.

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 goes beyond it by prescribing how projectIntent=explicit must be reasoned about (only explicit user selection or a just-created project, never name matching) and by treating idempotencyKey as a persisted artifact rather than a plain UUID. The stability and similarityBoost knobs get no prose treatment, which keeps it at 4 rather than 5.

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: 'Synthesize a confirmed script in a voice from voices_list into one standalone speech audio job (ElevenLabs)', and explicitly names the three siblings it is not (lipsync_create, dialogue-previews_create, translation-previews_create). An agent can choose between them without opening any 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?

Gives explicit preconditions (check speech-previews_get-options first, persist idempotencyKey before calling, verify projectId access) and explicit exclusions routing to the three alternative tools. It also states the recovery procedure after an uncertain response and forbids re-creating after an attach failure, which is exactly the when/when-not guidance this dimension rewards.

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