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

Annotations supply only readOnlyHint=true; the description adds value beyond them by declaring the login requirement and a visibility rule (the friend link of the other party is visible only to friends). That is exactly the kind of access-condition context annotations cannot convey. It does not cover failure behavior when unauthenticated, which keeps it from a 5.

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?

One semicolon-delimited sentence, front-loaded with the auth prerequisite and then the field set — nothing redundant. The compression is heavy enough that the clause about friend-link visibility reads as a fragment, but no sentence is wasted.

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 one-parameter read tool with no output schema, enumerating the returned fields and the visibility rule covers what an agent needs to interpret results. Only the error/unauthenticated path and target-id edge cases are unaddressed.

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 100% and the single parameter is documented as '目标用户 id'; the description adds no format, resolution, or edge-case semantics (e.g. whether self or nonexistent ids are valid) beyond the schema. Baseline 3 applies.

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 names the concrete fields returned (following, followedBy, isFriend, isSelf), which makes it clear this reports my bilateral relationship state with one target user rather than a generic user lookup. It stops short of positioning itself against nearby siblings like get_contact_exchange_state or list_my_network, so the boundary is inferred rather than stated.

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 one real prerequisite ('登录' – must be logged in) and implies the use case (checking whether I follow / am followed / am mutual with someone), but never says when to choose this over alternatives or what happens for an unknown or self userId. Usage is implied rather than guided.

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