speech_to_text

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

No annotations are provided, so the description carries the full burden. It mentions return behavior ('Returns: transcript text or file path'), which adds some value beyond the input schema. However, it doesn't disclose critical behavioral traits like rate limits, authentication needs, error conditions, or how the 'save_transcript_to_file' and 'return_transcript_to_client_directly' parameters interact. For a tool with 6 parameters and no annotations, this leaves significant gaps.

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 appropriately sized with two sentences that are front-loaded: the first states the purpose, and the second provides usage and return info. There's no wasted text, and it's structured for quick comprehension. However, it could be slightly more polished (e.g., combining clauses), but it's efficient overall.

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 complexity (6 parameters, no annotations, no output schema), the description is incomplete. It covers the basic purpose and return types but lacks details on parameter usage, behavioral constraints, error handling, and output format. Without annotations or an output schema, the description should do more to guide the agent, especially for a tool with multiple configuration options like diarization and output handling.

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 doesn't explain any of the 6 parameters beyond what the schema titles provide (e.g., 'input_file_path' is implied by 'audio' but not detailed). The description mentions return types related to 'save_transcript_to_file' and 'return_transcript_to_client_directly', but doesn't clarify their semantics or interactions. With low coverage and no parameter explanation, it fails to add meaningful value.

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: 'Transcribes audio to text' with a specific verb ('transcribes') and resource ('audio to text'). It distinguishes itself from sibling tools like 'text_to_speech' or 'isolate_audio' by focusing on transcription. However, it doesn't explicitly differentiate from potential similar tools (none in the sibling list), so it's not a perfect 5.

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 includes a 'Use when:' clause: 'converting speech recordings to text,' which provides basic context for when to use it. However, it lacks explicit guidance on when not to use it (e.g., vs. 'get_conversation_transcript' for existing transcripts) or alternatives, and doesn't mention prerequisites like file format support. This is implied usage rather than comprehensive guidance.

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