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

Annotations only declare the generic profile (readOnly=false, destructive=false, idempotent=true); the description adds the traits an agent actually needs: the target is never notified, the effect is scoped to the caller only, block is strictly broader than mute, staff/regulars cannot be blocked, and a shadow's mutes expire with its pass. These are non-obvious side effects not derivable from the schema or 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?

Front-loaded with a useful one-line summary, but the body repeats itself: 'Only you are affected, and they aren't told' appears three times, 'as anyone does' and 'For members' twice each, and the opening sentence pre-lists every action that the following paragraphs re-explain. The information is good; the packaging is bloated and reads as concatenated per-action blurbs.

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?

Five parameters with full schema coverage, no output schema, and a description that covers effects, privacy, eligibility and expiry. The one gap is `list`: it says whose lists are returned but not what the result looks like, which matters more here because no output schema exists.

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 the baseline is 3, and the description adds real constraint semantics on top: `who` must be someone in your room or staff when muting/blocking, but may be anyone previously actioned when undoing. `action` semantics are spelled out per value rather than left to the enum. It does not touch `key`, `shadow` or `idempotency_key`, which the schema already handles.

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?

Names five concrete actions (mute, unmute, block, unblock, list) against a specific resource (people addressed as player:/staff:/shadow:) and states the guarantee up front: 'yours alone, and they aren't told.' There is no ambiguity about what the tool does or which of its modes applies to which situation.

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 explicitly routes between the tool's own actions: mute stops words and gestures, block additionally stops whispers and drinks, and 'the staff and the house regulars serve everyone, so can't be blocked: mute them instead.' That is genuine when-to-use guidance. What's missing is guidance versus siblings outside the tool (e.g. report for abuse).

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