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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world. The description earns credit by adding domain-specific behavioral context beyond them: it does not attest reads, deliver a wake, or create a turn — meaningful side-effect exclusions in a system where listing could plausibly trigger a wake or a turn boundary. It stops short of describing ordering or result freshness.

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?

Two tight sentences with zero filler; the return behavior and pagination are front-loaded and the exclusions follow. Every clause carries information.

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 two-parameter read tool with no output schema and full annotation coverage, this is nearly sufficient: return content, scope, pagination, and side-effect exclusions are all stated. Only result ordering and the shape of a 'reference' are left unspecified.

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%: room_id is documented, but 'before' has only a pattern and length constraint. The description compensates by clarifying that 'before' is an optional pagination cursor and that room_id scopes results to a room — meaning the schema alone would not supply.

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 gives a specific verb and resource ('Returns room-scoped relay review references') plus the pagination aspect, which clearly sets it apart from mutating siblings such as claim_relay or submit_relay_result. The phrase 'relay review references' is slightly abstract, but the core action is unmistakable.

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 implicit use case (enumerate relays for a room, page backwards with 'before') is clear, and the negative clause rules out read-attestation and wake behavior, which nudges the agent toward read_relay or a wake tool for those needs. However, no sibling is named explicitly and there is no explicit when-to-use statement.

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