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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses meaningful behaviors: no access record is left, the author is not notified, the response is a frozen snapshot at creation time, and it excludes contact info, references, and attachments. It also states error conditions for revoked/expired/deactivated shares and advises not to retry with case changes. This adds substantial value beyond the structured 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 organized into clear labeled sections: when to use, chained alternatives, and behavioral semantics. Every sentence contributes distinct information, and there is no filler or repetition. The length is justified by the amount of decision-relevant context provided.

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?

The description covers the trigger, user intent, anonymous access, the follow-up chain, authentication requirements, return semantics (frozen snapshot), excluded fields, and error handling. Even without an output schema, the description sufficiently describes what the agent should expect and how to react to failures.

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 schema already covers the single token parameter with a pattern and description. The tool description adds practical context by showing the token can be extracted from a /cooperation/share/<token> URL tail, reinforcing how the agent should derive the parameter value. This is a useful supplement, though the schema already carries most of the semantic weight.

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 clearly states the tool's purpose: previewing the content of a cooperation share from a 43-character token or a /cooperation/share/<token> link, with anonymous read access. It also distinguishes itself from redeem_cooperation_share by framing preview as '先看看内容' and redemption as a follow-up action that leaves a record.

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 '【何时用】' section explicitly defines the trigger condition: the user has a share token/link and wants to preview content first. The '【组合链】' section gives concrete guidance on when to use redeem_cooperation_share and send_cooperation_interest instead, plus the auth prerequisite, making the decision boundary with siblings explicit.

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