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

Adds rich behavior beyond the annotations: 'Billed per character' discloses cost, and the async job contract (waits ~2 minutes, otherwise returns status queued/running, then poll get_generation) is exactly what an agent needs to invoke it correctly. Annotations only mark it as a non-destructive open-world write, so the description carries and delivers the real behavioral load.

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 tightly packed sentences, front-loaded with purpose, then billing, then the async contract. Every clause earns its place 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?

For a 6-param mutation tool with no output schema, the description covers cost, async lifecycle, and the polling path well. It does not say what the successful result actually contains (e.g., an audio URL/asset), leaving the agent to infer the artifact from get_generation.

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, but the description adds meaning by explaining the tier/model/params interaction — the voice comes from the tier's model unless passed in params — which clarifies how params and tier relate in practice. It stops short of explaining params keys or provider precedence beyond what the schema already documents.

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 — 'Generate speech (text-to-speech) for the title' — which distinguishes it reasonably from generate_music/generate_image/generate_video siblings. The title mentions 'or sound' but the description narrows to speech only, leaving a small mismatch with the advertised scope.

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 clear operational context: when the call returns synchronously versus when to 'poll get_generation with its id', and how the voice is chosen (tier's model unless overridden in params). It does not state when to prefer this over generate_music for non-speech audio, so sibling routing is only implied.

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