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

With no annotations, the description carries the full burden and does well: it discloses the 1,000-character cap, output encoding (base64 JSON), sample rate and channel count, the underlying model (MeloTTS), and a per-call price of $0.01 USDC on Base via x402. Payment mechanics and limits are exactly the behavior an agent needs before invoking. It stops short of stating what happens on over-length input or how payment failure surfaces.

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 compact sentences, each front-loading a distinct fact — purpose and output format, supported languages, then cost. No filler, no repetition of the tool name.

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 two-parameter tool with no output schema, the description supplies the return shape (base64 WAV in JSON), the size limit, and the pricing model, which covers what the schema cannot. The only gap is failure/error behavior for oversized text or unpaid requests.

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% and both parameters are documented in-schema, so baseline 3 applies. The description's language list essentially restates the `lang` enum and the character limit restates the `text` pattern, adding no syntax, default, or fallback detail beyond structured data.

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 opens with a precise verb+resource (text to speech) and immediately specifies the output artifact: a WAV file (22 kHz mono) returned as base64 in JSON. That output shape distinguishes it from audio-consuming siblings like ai_transcribe, though the description never names that sibling or any other alternative explicitly.

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?

Usage is implied by the name and the format details — an agent can infer it should call this when it needs spoken audio from text. There is no explicit when-to-use/when-not guidance and no routing statement pointing to ai_transcribe (the inverse direction) or ai_translate (for cross-language text).

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