blockrun_speech

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

Annotations only declare readOnlyHint=false, openWorldHint=false, destructiveHint=false, offering minimal safety info. The description adds rich behavioral detail: pricing structure ('$0.05/1k chars', 'min $0.001, quoted before payment'), model constraints ('max 3k chars in / 120s out'), prompt-directed behavior ('voice parameter is ignored'), and persistence guidance ('download immediately if you need to keep the file'). This goes far beyond the 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 dense but efficiently structured: intro line, bullet-style action list, model breakdown, voice aliases, and a crucial note about hosted URL expiration. Every sentence carries actionable information (pricing, constraints, defaults, exclusions) with no filler or redundancy.

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?

Given the tool's complexity (multiple actions, models, pricing, voice aliases, prompt-directed behavior), the description covers all critical aspects for selection and invocation: how to use each action, which model to choose, billing implications, input length limits, and output format. No output schema exists, but the description explains the return value (hosted audio URL) sufficiently.

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%, but the description adds substantial meaning: pricing per character for each model, voice alias list (sarah, george, etc.), default model and speed, sound effect pricing and duration limits, and the key nuance that seed-audio-1.0 uses input text for voice/emotion/staging. This enhances the schema for every parameter, not just repeating existing descriptions.

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, multi-action statement: 'speak text aloud (ElevenLabs or ByteDance Seed Audio), generate sound effects, list voices.' This clearly distinguishes the tool from sibling tools (e.g., blockrun_music, blockrun_image) and states the exact resources it acts upon.

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 explicit context for each action (speak, sound_effect, voices) and model usage (e.g., 'multilingual-v2 for narration', 'v3 most expressive', 'seed-audio-1.0 is prompt-directed'). It does not, however, state explicit exclusions or compare with sibling tools (e.g., 'for music use blockrun_music'), so it falls short of a 5.

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