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

No annotations are provided, so the description carries the full behavioral burden. It discloses the return content (transcript with keyword timestamps) but says nothing about accepted audio formats, size/duration limits, or auth requirements for a tool whose sole input is a base64 payload.

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?

Two compact sentences with the core function front-loaded and the keyword/segment capabilities following. No filler, though it is arguably under-specified rather than merely concise.

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 no annotations and no output schema, the description is the only source of information. It partially covers returns but leaves the single required input parameter and operational constraints (audio format, limits) unexplained, which is inadequate for a working call.

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?

There is one parameter (audio_base64) with 0% schema description coverage, and the description adds no information about it. The encoding expectation, supported audio formats, and any size constraints are left entirely undocumented.

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?

States a specific transformation ('speech-to-text') and goes beyond the name by naming distinguishing features: crypto keyword detection (bullish/bearish/dump/pump) and timestamped speaker segments. It is clearly distinguishable from the likely siblings (markets/alpha/infer), though it never explicitly contrasts with the 'tts' sibling.

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?

No when-to-use guidance and no alternatives named, despite 'tts' being an obvious counterpart tool in the sibling list. An agent must infer that stt is for audio input and tts for audio output solely from the acronyms.

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