speak

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

With no annotations, the description carries the full burden. It discloses the engine (local VoxCPM2) and that the result is a file path, which is useful, but says nothing about voice cloning via a reference audio, latency/cost of local inference, whether output files are overwritten, or how the control instruction actually steers emotion.

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?

Two short sentences, front-loaded with purpose then return value; no filler. It is efficient, though the brevity edges into under-specification given the parameter surface.

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?

Eight parameters, zero annotation coverage, and no output schema, yet the description explains neither the knobs nor the output beyond 'a file path'. For a TTS tool with a voice-reference parameter and a tunable control instruction, this is well short of what an agent needs to call it confidently.

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 description coverage is 0% across 8 parameters, and the description mentions none of them. The terms '情感旁白' hint that control_instruction drives emotional delivery, but seed, cfg_value, inference_timesteps, normalize_loudness, and reference_audio_path (a high-impact voice-cloning input) are left entirely opaque.

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 / emotional narration with local VoxCPM2) plus the return artifact (audio file path). It implicitly contrasts with the singing siblings (sing_notes, sing_metadata) by naming narration/speech, but never explicitly distinguishes itself from speak_segments.

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?

No guidance on when to pick this over speak_segments, when a reference voice should be used, or any prerequisites (model availability, GPU, language support). The agent must infer the single-utterance vs. segmented distinction from sibling names alone.

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