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

Beyond the annotations, it discloses the actual side effect (the dialog message content becomes "🎤Распознано: …"), that each call charges the project balance, and why backlog voice messages are not auto-transcribed. The per-call cost note also reinforces the non-idempotent hint in concrete terms.

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?

Three front-loaded sentences: effect, when to use, then cost and parameter sourcing. Slightly dense with the parenthetical transcription marker and the explanatory aside, but nothing is wasted.

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 only two required params, no output schema, and existing annotations, the description covers the missing pieces an agent needs: the write effect on dialog content, the billing implication, and how to source the message id.

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 coverage is 100%, so the baseline is 3; the description goes further by tying message_id to dosai_get_messages and restricting it to voice/audio message types. It adds no format or validation detail, but the schema already covers UUIDs for both parameters.

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 verb and resource ("Turn one voice message into text") plus the persistence effect ("save it in the dialog"). It is unmistakably distinct from siblings like dosai_get_messages or dosai_list_media, and an agent can tell what it produces from the description alone.

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?

Gives an explicit triggering condition ("a voice note that came while the bot was off in that dialog") and an explicit exclusion ("transcribe the messages you need, not the whole history") backed by the cost rationale. It also routes the agent to dosai_get_messages to obtain message_id where message_type is voice or audio.

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