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

The readOnlyHint=true annotation already establishes that this is a safe read operation. The description adds the authentication requirement, but it says nothing about pagination, result ordering, or whether the list is truncated, and those are real behavioral questions when listing every blocked user.

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?

Two compact clauses with no wasted wording. The authentication prerequisite is front-loaded before the action. The brevity is appropriate for a parameterless read tool.

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 zero-parameter, read-only listing tool with no output schema and full schema coverage, the description covers who is listed and the auth requirement. The only notable gap is any hint about pagination or result size, which is a minor omission at this complexity level.

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 the baseline score is 4. The description correctly implies that the scope is always the current user's own blocklist, with no filtering options to document.

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 uses a concrete verb and resource: "列出当前用户拉黑的所有用户" (list all users blocked by the current user). An agent can immediately tell that this is the read side of the block_user and unblock_user pair. It does not explicitly name or differentiate itself from those siblings, which keeps it from scoring 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?

The leading "登录;" clause states a prerequisite: the caller must be authenticated, which is useful context. However, the description never says when to prefer this tool over alternatives, such as querying a user profile or block status, and it names no exclusions.

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