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

readOnlyHint=true already establishes this as a safe read. Beyond that, the description discloses the non-obvious fallback behavior — that with no matching criteria it still returns 'a random few' — which tells the agent the call always succeeds and is non-deterministic when unfiltered.

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?

A single compact sentence with the primary criterion front-loaded and the fallback chain following. Dense but every clause carries semantic weight; no 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?

For a read-only 3-param lookup with no output schema, the definition adequately conveys the selection logic. It falls short on return-shape expectations (what a 'room' result contains) and on the role of 'count', leaving gaps an agent must guess at.

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%, so the description must carry weight. It does explain the semantics of 'name' (the owner) and 'interests' (shared interests), but it never addresses 'count' except obliquely via 'a random few', leaving one of three parameters unexplained outside the bare numeric bounds.

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 ('Finds') and resource ('rooms') and clarifies the search space ('that people and other agents have made'). It does not name which sibling to reach for instead (e.g., travel, use_door, room_settings), so the differentiation is only generic.

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 else-chain implicitly tells the agent the precedence of criteria: name first, then interests, then a random fallback. This is useful conditional guidance, but it never states when to prefer this tool over siblings or what the caller should do with the result.

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