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

Annotations only declare destructiveHint=false, so the description carries the real behavioral burden and does it well: it discloses that the reason is shown to both the counterpart and their organization host, that no reply is guaranteed, that no SMS is sent automatically, and that the default call is a non-committal preview gated by previewHash. These are exactly the side-effect and consent facts an agent needs before mutating state.

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 login requirement and conversation restriction are front-loaded, and the preview flow is laid out in a compact arrow sequence with almost no filler. The telegraphic style and bracket notation make it slightly dense to parse, but every clause carries operational information.

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 only destructiveHint=false and no output schema, the definition covers the essentials: preconditions, disclosure audience, preview/confirm handshake, and the no-reply/no-SMS caveats. It does not say what the preview response contains or how long a previewHash stays valid, which are the remaining small gaps.

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 it mostly does: reason must come verbatim from the user, consent must be true, preview defaults to true, previewHash is the confirmation token paired with preview=false, and conversationId must be the user's own two-person conversation. Only minor redundancy with schema const/default values keeps it from a 5.

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 a specific operation: sending a request to a conversation counterpart's organization host to help make contact, with the reason disclosed to them. The scope constraints ('仅本人双人会话') make it distinguishable from related tools such as request_contact_exchange or request_activity_cloud_relay. It never explicitly names a sibling alternative, so it stops short of a 5.

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 clear preconditions (login required, must be the user's own two-person conversation, consent must be true, reason supplied by the user) and an explicit never-do ('不能代填或暗中转达'). The preview→confirm→execute sequence tells the agent exactly how to invoke it. No comparison against sibling request tools is offered, so no exclusion guidance beyond the conversation-ownership rule.

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