Generate speech

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

Annotations only indicate read/write and open-world hints. The description adds significant behavioral context: the 1000-character limit (including markup), that prosody parameters wrap text in AI Director tags and force the caruso model, that text becomes literal (escaped) when prosody is used, and that inline tags should not be mixed with prosody. This goes far beyond what annotations provide.

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?

The description is concise and front-loaded: the first sentence states the core purpose, the word 'Synchronous' is a compact critical qualifier, and the remaining sentences cover the essential caveats (length limit, prosody behavior, inline tag handling) without redundant filler. Every sentence contributes distinct information.

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?

With 12 parameters, no output schema, and no explicit return type, the description covers the essential operational context: synchronization, disk output, character limit, and the prosody/tag interaction. It does not describe the response payload, but it does mention optional inline base64 audio (embed_audio) and the file-saving behavior, which partially compensates for the missing output schema.

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?

While the schema covers 100% of parameters with descriptions, the tool description adds crucial meaning: that pitch/tempo/loudness force the caruso model and cause the text to be treated as literal (escaping special characters), and that inline tags require leaving those parameters unset. This clarifies interactions not fully captured in the schema.

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 specific verb+resource: 'Convert text to speech with a WellSaid voice and save it to disk.' It also explicitly states 'Synchronous,' which distinguishes it from the async sibling wellsaid_create_clip_async, and its focus on direct speech generation differentiates it from wellsaid_generate_speech_with_timing.

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?

The description provides clear usage context: it is synchronous, requires obtaining a speaker_id from wellsaid_list_voices first, and explains when to avoid passing prosody parameters (if hand-authoring inline tags). It does not explicitly name alternative tools but gives strong contextual guidance and exclusions for the main usage pattern.

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