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

Annotations declare destructiveHint=true, openWorldHint=true, and idempotentHint=false, so the description's job is lighter. It adds valuable behavior: the operation is SYNC ('the audio URL comes back in the result') and it exponentiates cost ('SPENDS CREDITS per-model, see creditCost'). It does not describe rate limits or failure modes, so it falls short of a 5.

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-loads purpose and model routing, then closes with two critical constraints (SYNC, SPENDS CREDITS). Dense but single-paragraph; the model catalog enumeration is slightly list-heavy but earns its place by covering the four supported models.

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 12-param, non-idempotent, credit-consuming generation tool with no output schema, the description covers the essential agent needs: model selection, delivery mode (SYNC), and cost. The main gap is undisclosed semantics for roughly half the parameters and no mention of failure/retry behavior.

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 50%, so half the parameters rely on the description. The description illuminates a few of them well (voice for ElevenLabs, duration in seconds, lyrics for songs) but says nothing about pitch, speed, volume, outputFormat, instrumental, referenceImageUrl, or referenceAudioUrls. Baseline 3 is appropriate given partial coverage.

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+resource ('Generate audio') and enumerates the exact model catalog it draws from (Seed Audio, MiniMax Music 3.0, ElevenLabs Music, ElevenLabs v3), explaining what each produces. This clearly distinguishes it from sibling studio_generate_image and studio_generate_video.

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?

Provides strong model-selection guidance ('Seed Audio makes dialogue... ElevenLabs v3 is expressive text-to-speech') and points to list_studio_models with mode='audio' for keys. It does not explicitly state when NOT to use this tool versus alternatives, but the per-model routing covers the main decision.

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