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

Annotations already establish readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description still adds real value by ruling out side effects an agent might otherwise assume: no file byte delivery, no read attestation, no native wake trigger. That is behavioral context beyond the structured hints.

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 sentences, front-loaded with the return payload and followed by explicit exclusions; nothing is redundant. It is terse to the point of being jargon-saturated, but not padded.

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?

There is no output schema, and the description compensates by naming what comes back (capsule, canonical assignment, frozen answer/source references, result descriptor, allowed verdicts). Combined with the exclusions, an agent has enough to call it correctly, with only the relay_id provenance gap outstanding.

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 carries an OAuth-consent description while relay_id has only a pattern and length. The description mentions relay_id solely as the lookup key and adds no format, origin, or acquisition guidance (e.g. where a relay_id comes from), so it does not compensate for the undocumented parameter.

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+resource ('Returns the review capsule... for relay_id') and enumerates the payload contents, which separates it from list_relays and submit_relay_result. It is dense with domain jargon, so an agent unfamiliar with 'capsule' or 'canonical assignment' gets less than a plain-language verb would give, but the operation is identifiable.

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?

Usage is conveyed only negatively: 'Does not deliver file bytes, attest reads or start a native wake,' which implicitly routes the agent to read_file/read_attachment, ack, and wake tools. There is no positive statement of when to call this rather than list_relays or room_situation, so the guidance is implied rather than explicit.

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