speech_to_text

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: the tool makes an external API call to Whissle (implying network dependency and potential latency), incurs costs, saves output files to disk (with default directory behavior), and returns both transcription text and file path. It doesn't mention error handling or rate limits, but covers the essential operational traits.

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 well-structured with clear sections (purpose, warning, args, returns) and front-loaded key information. Every sentence earns its place: the first states the core function, the second explains default behavior, the warning is critical, and parameter explanations are necessary given 0% schema coverage. It could be slightly more concise in parameter explanations but remains efficient.

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 (external API call, file output, multiple parameters) and lack of annotations, the description provides complete context. It covers purpose, cost implications, parameter semantics, default behaviors, and output format. The presence of an output schema means the description doesn't need to detail return values, and it adequately addresses all other aspects needed for effective tool use.

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%, so the description must compensate. It provides meaningful semantics for all parameters: explains what 'audio_file_path' is for, clarifies 'model_name' default and purpose, defines 'timestamps' as word-level inclusion, explains 'boosted_lm_words' and 'boosted_lm_score' for recognition boosting, and details 'output_directory' default behavior. This adds substantial value beyond the bare 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 clearly states the tool's purpose with specific verbs ('convert speech to text', 'save the output text file') and distinguishes it from siblings like 'diarize_speech' (which focuses on speaker separation) and 'list_asr_models' (which lists available models). It specifies both the core transformation and the file-saving behavior.

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 usage guidance: 'Only use when explicitly requested by the user' due to cost implications, and distinguishes when to use this tool (for transcription) versus siblings like 'summarize_text' or 'translate_text' (which process text rather than audio). The cost warning serves as a clear when-not-to-use criterion.

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