transcribe

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose one important non-obvious behavior: the result is written into an archive rather than merely returned, so the call mutates stored state. Beyond that it says nothing about permissions, whether existing archive entries are overwritten, how long transcription takes, or how failures for individual ids are reported.

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?

A single compact sentence with no filler, and the resource plus the write-to-archive effect are front-loaded. It is efficient, though brevity here comes at the cost of the missing details noted above rather than from tight editing of rich content.

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?

An output schema exists, so return values need no explanation. But this is a mutation tool with zero annotations, an undocumented chat parameter, and batch-style input, and the description supplies none of the operational context (auth, idempotency, partial failure, what the archive is) an agent needs to invoke it safely.

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 and does not. "С указанными id" loosely maps to the ids array but never says whether these are message ids, media ids, or file ids, and the required chat parameter is not mentioned at all, leaving its expected format (numeric id, @username, dialog title) undefined.

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 ("Расшифровывает" / transcribes) and a specific resource (voice messages and round video notes identified by the given ids), plus the side effect of writing the text into an archive. That clearly separates it from fetch_media or send_message, but it never names a sibling it is meant to replace, so the differentiation is implicit rather than explicit.

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?

Usage is only implied by the object of the verb: call this when you have ids of voice/round-video messages that need converting to text. There is no explicit when-to-use, no when-not, no mention of the obviously overlapping siblings describe_media or fetch_media, and no prerequisites such as first resolving ids via list_dialogs or sync_chat.

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