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

Adds real value beyond readOnlyHint=true: an authentication requirement, the fact that results are filtered by audience/block/hide settings, that INVITED entries are retained with their true participation status, and an explicit caveat that a match does not imply an attendance commitment. That last caveat materially changes how an agent should report results. It does not describe pagination or the response shape, 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?

Front-loads the login gate in a bracketed marker, then gives scope, data semantics, and the follow-up path in two tight clauses. Very little waste, though the telegraphic slash-separated phrasing ('受众/屏蔽/隐藏') is denser than it needs to be for non-Chinese-native readers.

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 single-parameter read-only list with no output schema, the description covers the login requirement, the filtering model, the interpretation caveat about INVITED and attendance, and the handoff to the connection-request flow. Nothing an agent needs in order to call it and act on the result is missing.

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?

Only one parameter (activityRef) and schema description coverage is 100%, so the schema already carries the semantics of '活动 id 或 slug'. The description adds no format or edge-case detail about the reference beyond implying the list is scoped to a single activity. Baseline 3 is appropriate when the schema does the work.

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?

States a specific verb and resource ('查本人匹配' for a given activity) plus the scope rule that results are governed by the caller's audience/block/hide settings. An agent knows exactly which list this returns. It does not name distinguishing siblings such as get_my_activity_match_group or list_my_organization_matches, so it lacks explicit sibling differentiation.

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?

Gives a clear precondition ('需要登录') and an explicit next-step routing rule: once the user consents, use create_connection_request, while cloud users go through the manual relay path. It stops short of saying when to prefer this over the adjacent match tools, but the when-to-use context (browsing worthwhile people at this event) and the follow-up path are both clear.

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