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

Annotations only say it is a non-read-only, non-destructive, non-idempotent write. The description adds genuinely non-obvious behavior: delivery is limited to the two participants, the message persists encrypted until either party deletes it, forget is the one exception, and per-tier rate limits (10s member / 30s shadow) govern how often it may be sent.

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 the core action and proximity rule, but it is padded with parentheticals and repeats the pacing rule ('one message every 10 seconds for a member, 30 for a shadow') that also appears in the text parameter, plus a trailing fragment 'For members.' that duplicates the earlier eligibility statement.

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?

With no output schema, the description carries return-value burden, and it does explain the observable outcome (the room shows it to the two of you alone) and persistence. It does not describe what a successful response contains or what an error reply looks like, leaving a small gap for a mutation tool.

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, but the description adds meaning the schema lacks: it clarifies the 'to' identifier is the room's naming ('to Ada, at the bar') and constrains 'text' with tighter business limits (280 chars member, 140 shadow) than the schema's maxLength of 2000. The 'shadow' tier is referenced without being defined, which keeps it from a 5.

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 resource — private one-to-one messaging to a single named recipient — and the clause 'The room shows it to the two of you alone' makes the private scope explicit, distinguishing it from broadcast siblings like say or comment. It stops short of naming the sibling it replaces, so an agent must infer the contrast with say/tell.

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 clear precondition (recipient must be within a few metres) and an explicit remedy when it is not met: 'If they are too far, walk closer first,' which points the agent at the walk sibling. Also states eligibility ('For members.') and pacing. No explicit when-not or full alternatives list, keeping it at 4.

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