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

Goes beyond the annotations by disclosing that each call costs a few cents from the project balance and that no real client data is affected. It also implies non-idempotency by describing history-based conversation continuation. It does not detail rate limits or failure modes, but the cost and side-effect disclosure is genuinely useful.

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?

Four short sentences, front-loaded with the core action and immediately followed by the key constraint (no real client), then history, cost, and use case. No filler.

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?

For a 3-parameter tool with no output schema, the description covers what it does, what it returns (the bot's real answer), the cost, and the safety boundary. Nothing an agent needs to invoke it correctly is missing.

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 100%, so the schema already documents project_id, message, and history. The description adds the intent of history (continuing a conversation) but no format or syntax detail beyond the schema, so baseline 3 applies.

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+resource: send a message to the bot as a client would and get the bot's real answer. It explicitly scopes this as a test chat that does not touch real clients, which separates it from sibling tools like dosai_get_conversation or dosai_send_operator_message.

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 a clear trigger: use it to check an answer after changing the prompt or the knowledge base. It also frames the exclusion ('without touching any real client'), though it does not name a specific alternative tool for comparison.

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