chat_certificate_create

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

Annotations provide minimal info (readOnlyHint=false etc.), but description adds significant behavioral context: asynchronous operation requiring polling, dependencies on prior calls, and constraints like chatMessagesFrom must be after registeredAt. No contradictions.

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?

Description is information-dense and front-loaded but could be better structured (e.g., bullet points). No unnecessary words, but readability could be improved.

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?

Covers prerequisites, parameter constraints, and async polling. Missing a brief note about the initial response (e.g., returns a certificate ID to poll), but the polling instruction suffices. No output schema, so description should guide result retrieval, which it does.

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 coverage, description compensates by specifying id format (UUID v4), timestamp format (ISO, chatMessagesFrom after registeredAt), and language enum. Provides clear instructions beyond the schema.

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 clearly states it creates a certificate of a range of messages from a certified chat. It is distinct from sibling tools like chat_certificate_get, which is for polling.

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?

Provides explicit prerequisites (chat_create, caseFileId, chat_get, messages in Telegram channel) and warns when not to use (if registeredAt missing). Also specifies async polling with chat_certificate_get until status CERTIFIED.

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