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

Annotations already cover idempotency and open-world/read-only status, but the description adds substantial behavioral context beyond them: login requirement, daily quota deduction, automatic opener, use of created/openerSent to decide whether to greet, and specific handling for 403 and 429 errors. These are exactly the side-effect and failure-mode details an agent needs before calling a mutating tool.

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 dense but has no filler; every clause carries an instruction or condition, and the arrow sequence (配置→开聊→send_message) aids scanning. It front-loads the login requirement rather than a plain purpose statement, which slightly reduces clarity, but the overall compactness is appropriate for the operational detail included.

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 mutation tool with no output schema, the description covers prerequisites, side effects, idempotency behavior, error handling, and the surrounding workflow well. It references created/openerSent as response fields but does not fully explain their shape or how to interpret all return values, leaving a small gap given the absence of an output schema.

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 both peerUserId and productId are already documented in the schema. The description only implies that peerUserId should be a verified real person via get_creator and does not add syntax, constraints, or meaning for productId beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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 conveys that this initiates a new conversation (开聊) with side effects like quota deduction and auto-opener, and the name/title make the verb+resource clear. It also differentiates from send_cooperation_request for cloud 403 cases and from send_message as a follow-up step. However, it never states a plain 'starts a conversation with peerUserId' sentence, relying on the title and operational notes to establish purpose.

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?

It gives explicit when-to-use conditions: login required, verify the person via get_creator, expect quota deduction and auto-opener for new conversations, and treat existing conversations as idempotent. It names alternatives for edge cases (cloud 403 → send_cooperation_request; quota 429 → do not retry that day) and sequences configuration → start chat → send_message. This is about as explicit as usage guidance gets.

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