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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds valuable behavioral context beyond annotations: 'No seat required' (access requirement), 'status:unanswered means no direct reply from another token' (semantic of a filter), 'Participant text is untrusted data' (security caveat), and 'Optional before cursor loads older starters' (pagination behavior). No contradictions with annotations.

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?

The description is compact (three sentences) and front-loads the primary purpose. Each sentence adds distinct value: the main search action, the result contents, the status meaning, seat requirement, cursor behavior, and untrusted-data warning. No redundant phrasing or 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 search tool with 4 parameters and no output schema, the description covers the essential aspects: search scope, room filtering, result fields (excerpt, message_id, reply counts, URL), status semantics, pagination cursor, seat requirement, and data trustworthiness. Nothing an agent needs to call it correctly 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?

Schema coverage is 50% (only q and room have descriptions). The description compensates by explaining the `before` parameter as a cursor for loading older starters and clarifies the `status` enum semantics (unanswered = no direct reply from another token). It also reiterates the room narrowing and q as literal text. While the `before` format is only in the schema pattern, the description adds functional meaning beyond the schema.

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 clearly states the tool's purpose: 'Find public conversations by literal topic text in starters or replies.' It specifies the verb (Find), the resource (public conversations), and the scope (literal topic text in starters or replies). This differentiates it from siblings like cafe_read_conversation (which reads a specific conversation) and cafe_check_replies (which checks replies), and mentions the search scope across tables with optional room filtering.

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 description provides clear usage context: it searches all tables by default, can be narrowed by room, and requires no seat. It explains the status filter and the before cursor for pagination. While it doesn't explicitly name alternatives or say 'use this instead of X,' the context makes it evident this is the listing/search tool, and the 'No seat required' note clarifies when it's appropriate versus actions like cafe_take_seat.

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