tg_transcribe

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

Given no annotations, the description carries the burden and discloses key behavioral traits: the 'auto' engine tries Telegram first (instant, free, voice/round only), then Groq, then local; limits are noted (max 20); and language improves accuracy. It doesn't explicitly state read-only behavior, but the transcription nature is clear and no destructive side effects are implied.

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 purpose is front-loaded in the first sentence, followed by a clean, scannable Args list. Each parameter explanation is one concise line, with no fluff or repetition. It's appropriately sized for a 6-parameter tool.

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 tool has an output schema (not shown) and the description covers all input semantics, engine behavior, limits, and optional language. It provides enough context for an agent to select and invoke it correctly, including parameter interactions (message_ids vs. kind vs. limit). No critical missing information for this use case.

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?

The description adds rich meaning beyond the bare schema: it explains each parameter's purpose, default behavior (e.g., 'Omit to take the most recent items of kind'), engine choices, and language usage. With schema description coverage at 0%, this fully compensates and even clarifies edge cases like message_ids vs. kind.

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 begins with a clear, specific action: 'Turn voice messages, round videos, music and video into text.' This distinguishes it from sibling tools like tg_translate (translation) and tg_summarize (summarization) by its focus on transcription.

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 clear context on how to use the tool, including selection of media kinds (voice, round, music, video, media, file) and the engine fallback order. It doesn't explicitly mention alternatives or when not to use, but the usage path is well implied through parameter explanations.

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