Generate Speech (TTS)

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

The description discloses a key behavioral trait—'Submits async—poll the returned request_id with xbrush_get_request'—which adds value beyond the annotations. It also notes model-specific requirements. However, it doesn't detail what happens on failure or whether partial output exists, though the annotations already cover readOnly/destructive/idempotent hints. No contradiction with annotations.

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, well-structured, and front-loaded with the core purpose. It uses a short intro followed by clearly labeled argument bullets. Every sentence adds useful information without redundancy or filler, making it easy to scan.

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?

The description provides complete context for a tool with no output schema: it names all parameters, explains conditional requirements, and tells the agent how to follow up (xbrush_get_request). The async nature and model-specific voice_id needs are covered. No output schema exists, so the tool adequately guides the agent through the full invocation flow.

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 100%, and the description largely repeats the same parameter details already present in the input schema (e.g., voice_id requirements, default speed range, model examples). It consolidates the information readable but does not add significant new meaning beyond the structured schema definitions. Baseline 3 is appropriate.

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 clearly states the tool's purpose: 'Generate speech audio from text using an XBrush TTS model.' This is a specific verb+resource combination that also distinguishes this text-to-speech tool from sibling tools like image, video, music, and sound effect generation. The model family details reinforce the tool's unique 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?

Usage guidance is explicit: it distinguishes when a voice_id is required (Minimax models) versus not (ElevenLabs), directs users to xbrush_list_voices for obtaining a voice, and explains the asynchronous workflow with 'poll the returned request_id with xbrush_get_request.' This provides clear when-to-use and prerequisite context beyond mere tool naming.

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