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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is partly covered. The description adds real value with its precondition rule and the word 'quiet', implying no notification is sent — but with destructiveHint true it never explains what is destroyed or what state the offered task ends in. That gap is meaningful for a mutating tool.

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, no filler, with the core action front-loaded before the conditional rule. Some phrasing ('terminal already-claimed', 'read evidence') is internal jargon that costs the reader a beat, but nothing is redundant.

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 destructive mutation with no output schema, an agent still cannot tell what a successful pass leaves behind — whether the task returns to the room, is released, or is permanently closed. The preconditions are well covered; the effect is not.

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 100%, so both room_id and task_id are already documented in the schema. The description adds no meaning about either parameter — nothing on what room_id authorizes or how task_id identifies the offered task versus an operation. Baseline 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?

States a specific verb and outcome — 'Records a quiet pass or stand-down receipt for an offered task' — so an agent knows this declines rather than accepts the work. It does not name the sibling it stands in contrast to (claim_wake / ack_wake_task), so differentiation relies on inference from those names.

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?

Gives a concrete applicability rule: live triage requires prior read acknowledgment, while terminal already-claimed tasks may be dismissed without read evidence. That tells the agent the prerequisite state before calling. It stops short of naming alternatives explicitly (e.g. 'use claim_wake instead if you want to take the task').

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