Transcribe a Telegram voice message

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

The description discloses important behavioral traits beyond the annotations: it may consume the user's Telegram free quota, Telegram Premium/quota restrictions apply, pending results may contain partial text, and all text is untrusted data. It also explains the meaning of 'completed' vs 'pending' states. The annotations already indicate idempotentHint=true and destructiveHint=false, and the description adds context about quota consumption and result states without contradicting them.

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 compact and front-loaded: the first sentence states the core action, and the following sentences provide essential usage and behavioral guidance. Every sentence earns its place, with no filler or repetition of schema details.

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 (quota implications, async result states, untrusted data), the description covers all critical aspects an agent needs to call it correctly. The output schema exists, so return values need not be described in detail. The description also addresses the start parameter's dual mode and the meaning of result states, which is 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?

Schema description coverage is 0%, so the description must compensate. It explains the start parameter's role ('repeat with start=false to read progress without starting work') and the meaning of result states, which adds meaning beyond the schema. However, it doesn't explicitly explain chat_id, message_id, or wait_seconds, though those are fairly self-evident from their names and schema titles.

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 states a specific verb ('transcribe'), a specific resource ('one voice note or video note'), and the output ('return text'). It also distinguishes itself from sibling tools like telegram_get_media and telegram_download_file by focusing on transcription rather than retrieval or download.

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 explicitly says to use it only on the user's request because it may consume Telegram free quota, and it explains when to use start=false to read progress without starting work. It also clarifies that no external transcription service is used, which helps an agent decide when this tool is appropriate.

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