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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description discloses multiple important behaviors: the invitee is notified, valid pending invitations to the same person are reused, there is no persistent or concurrent deduplication guarantee, and no persistent request dedup key exists. This materially affects how an agent should invoke and verify the call. No contradiction with annotations.

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 compact and information-dense: each sentence adds a distinct constraint or caveat, and the core action plus login requirement is front-loaded. It is structured and free of filler, though the density makes it slightly harder to parse quickly.

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 mutating tool with no output schema and no parameter descriptions in the schema, the description covers the main operational risks: authorization, notification side effects, scope limitation, non-idempotency, dedup limits, and timeout handling. It even gives partial return information by stating what the response excludes. It does not describe the success response shape or the exact meaning of message/contribution, so minor gaps remain.

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 for the four parameters, but it only refers to them indirectly via phrases like '指定站内用户' and '目标发起人'. goalId and inviteeId can be inferred, but message and contribution are never explicitly explained, and the required parameters are not called out in the description. The global context helps, but per-parameter meaning is largely left to inference.

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 concrete action: the target initiator sends a collaboration invitation to a specified in-site user and the user is notified. It also narrows scope with '仅支持站内定向邀请' (only targeted in-site invitations), which distinguishes this from external or bulk invitation flows. This is far more specific than the tool title alone.

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 description gives explicit prerequisites and boundaries: login is required, prior authorization of the invitee and content is needed, only on-site targeted invitations are supported, and the response will not contain phone numbers or forwardable tokens. It also tells the agent what to do on ambiguous results or timeout: query current state first and do not auto-resend. This is strong operational guidance.

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