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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and closed-world scope, so the safety profile is covered. The description adds real behavioral context beyond that: results are limited to what the connection's scopes permit, message text is never searchable, and nothing involving someone under 18 is ever returned.

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-loaded with the core action and resource list, then tacks on the return contract and the permission/age constraints. Dense but every clause carries information; only the em-dash parenthetical about message text could be tightened.

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?

An output schema exists, so return values need not be explained, yet the description still notes the id-based return contract. It covers permissions and content exclusions thoroughly; pagination and result-count limits are the only notable omissions for a search tool.

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?

With 100% schema description coverage and only one parameter, the schema already explains that empty query means recent items and gives examples. The description adds nothing further about query syntax or matching behavior, so the baseline of 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 verb (search) and enumerates the exact resources searched — conversations by participant/room name, plans, model hunches, members' public profiles — and explicitly excludes message text. This distinguishes it from siblings like search_profiles, find_people, and list_conversations without needing to open any 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 states the follow-on workflow ("Returns ids to open with fetch"), which is useful routing guidance, but never names an alternative tool or the condition that would select one over this. Usage is implied by the resource list rather than stated as explicit when/when-not guidance.

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