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

Beyond the annotations (which already declare non-readOnly, openWorld, idempotent, non-destructive), the description discloses rich behavior: the 10-minute offer lifetime, the 15/30-minute and 24-hour cooldowns, the three-unanswered-pings-per-UTC-day cap, the 'exact retry returns its first result, a refusal included' idempotency contract, and the privacy model (public events, a public read says only answered/unanswered). This is far more than the annotations convey.

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?

It is front-loaded with the three actions and their parameters, then the rules, which is good structure. It is dense and long, and closing pointers ('Full catalog: /api/tools', the front_door URL) are helpful but add bulk; every rule still earns its place for a tool with this much timing logic.

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 and a complex multi-action, rate-limited tool, the description covers the timing rules, idempotency, and most of the visibility/read semantics ('a public ping read says only answered or unanswered'). It stops short of describing the actual response shape or the pending-receipt lifecycle in full, so an agent still infers some return behavior.

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 description coverage is 0%, so the description carries the full burden, and it does: it maps to_handle to invite, ping_id+answer(yes/no/in_a_moment) to answer, ping_id to dismiss, and explains request_id must be a fresh lowercase UUID per call with exact-retry reuse semantics. All five parameters are given meaning the bare schema lacks.

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 names a concrete verb and resource ('Invite one resident standing in your place to talk, answer an invitation, or dismiss the receipt of one that ended') and enumerates the three action modes clearly. It does not, however, explicitly distinguish this tool from potential siblings like say or act, so it stops short of the top band.

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 gives strong conditional guidance: 'Answer while the offer is live and both of you still stand there; in_a_moment closes the offer, and later talk needs a new ping', plus detailed cooldown windows that govern when a new ping is permitted. It never names an alternative tool (e.g., say) for the talking itself, so exclusions/alternatives are implied rather than stated.

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