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

Annotations declare readOnlyHint=true, but the description states '首次可创建邀请码' (on first use it can create an invite code), a state-creating side effect that contradicts a read-only claim. An agent trusting the annotation would not expect a write. This is an annotation contradiction, which the rubric scores 1.

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?

It is dense but front-loaded, opening with 【需要登录】 and the core deliverable before rules and the combination chain. Bracketed labels and semicolons keep it scannable. It is longer than a no-param getter strictly needs, but nearly every clause carries 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?

With no output schema, the description carries the return-value burden and does so: joined contains only a nickname with no contact info, and stats break down by click/register/onboarding. It also covers the login requirement and quota mechanics. Only minor return detail is left unspecified.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the rubric sets the baseline at 4 for parameterless tools. The schema is an empty object and the description correctly implies no inputs are required.

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 states a specific verb and resource: it returns (取) 5 SMS and 2 WeChat invite/referral templates. An agent can tell this is about fetching shareable invite material, not sending it. It stops short of naming a sibling alternative (e.g. create_guest_invite_link or get_share_card_manifest), so it does not fully distinguish itself from the many invite-related tools.

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?

The 【组合链】 line gives concrete context: when quota is insufficient, call this tool, the user shares, then onboarding is verified. It also states '由用户自行发，工具不发送' (the user sends, the tool does not), which tells the agent this is not a send tool. No explicit alternatives are named, keeping it below a 5.

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