tg_transcribe

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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses the engine fallback chain in detail: auto tries Telegram first (with Premium/quota constraints), then Groq, then local. It also explains that Telegram transcription only supports voice and round, and is skipped without a request when the account lacks eligibility. This adds meaningful behavioral context that annotations do not provide.

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 statement is front-loaded and the Args block is compact and organized by parameter. The engine explanation is the longest part but is necessary because the auto behavior has real conditions. No filler or redundant information is present.

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 description covers the core selection and execution aspects: media types, message selection, kind values, limits, engine options, and optional language. The main omission is the return format—whether the tool returns a single transcript, per-message text, or errors for items without speech—but given that no output schema exists, the description is still largely sufficient for correct invocation.

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?

With 0% schema description coverage, the description is the sole source for parameter meaning. It explains all six parameters: chat, message_ids, kind, limit, engine, and language, including value sets, defaults, max limits, and conditional behavior. This fully compensates for the empty schema 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 verb and resource: 'Turn voice messages, round videos, music and video into text.' This clearly identifies what the tool does and its media scope. It does not explicitly differentiate from siblings like tg_translate or tg_summarize, but the transcription purpose is evident from the first sentence.

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 operational guidance, such as 'which media tab to pull from when message_ids is omitted' and how the engine fallback behaves. It establishes a clear context for when this tool is appropriate, though it stops short of naming alternatives or stating when not to use this tool.

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