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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds substantive context beyond that: which match categories are included, the special free weekly curated match, and the exact per-item payload (match_id, other member, status, last message, unread count) — particularly valuable because there is no output schema. It does not discuss ordering or whether limit applies per category or overall.

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?

Three sentences, each earning its place: scope first, then retrieval triggers, then return shape. The lead clause front-loads the resource and the example questions are dense retrieval cues rather than filler.

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?

With no output schema, the description correctly compensates by describing the item fields, and it covers the non-obvious free weekly curated match. Remaining gaps are the 'declined' category relative to the default 'all' status and pagination/limit behavior, which an agent would need to reason about for large accounts.

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 coverage is only 33%: join_code is documented, while limit and status rely on bare type/default/enum metadata. The enumerated categories loosely map onto the status enum, but the description never mentions the 'declined' value or explains that the default status='all' may surface matches outside the three named categories, and it does not clarify whether limit (default 30, max 100) is a global page size or per-category. Some added meaning, but an important gap remains.

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 a specific verb (List) and resource (the user's introductions) and immediately enumerates the three scopes covered: accepted matches with an open chat (including the free weekly curated match), inbound requests awaiting the user, and unanswered outbound requests. That scope is clearly distinct from siblings such as read_thread (message-level), search_members/browse_directory (discovery), and respond_to_request (mutation), so an agent can route without opening the schema.

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 explicit trigger questions ("did anyone reply", "any new introductions", "is anything waiting on me", "who have I connected with"), which is strong positive guidance for a status-listing tool. It stops short of naming alternatives or exclusions — e.g., that reading message bodies requires read_thread and acting on a request requires respond_to_request — so the routing is clear but not fully bounded.

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