Speak

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

With no annotations, the description carries the full burden and does most of it: it discloses the output encoding and format (base64 MP3, 64 kbit/s mono), the hard 1,000-character input ceiling, the engine, and the multi-call strategy for long input. It stops short of error behavior, latency, and whether the base64 string carries a data-URI prefix.

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 tight sentences: capability and output format first, then voice/language coverage, then speed and the long-text workaround. No sentence is filler and the most important constraint (the 1,000-character cap) is front-loaded.

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?

There is no output schema, so the description appropriately specifies the return format and encoding, and no annotations mean behavioral traits had to be stated — largely done. Only peripheral details (errors, latency, response envelope) are omitted, which an agent rarely needs before calling.

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 67%, and the description fills the gaps: it explains that the voice id picks the language (spanning seven languages), that speed ranges 0.5–2.0, and reiterates the character limit for text. The voice letter-code semantics are covered in the schema's own enum description, so the description adds breadth (language set) rather than decoding detail.

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 (turn text into natural speech) and immediately names the engine (Kokoro 82M) and the exact return artifact (MP3, 64 kbit/s, mono, base64). An agent knows precisely what the tool produces without inspecting anything else.

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 actionable context for the main edge case: text over 1,000 characters should be split at sentence ends with one call per part. No alternatives exist to route against, so there is no exclusion guidance to give, but the practical when/how is explicit for the realistic failure mode.

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