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

Annotations cover only the safety profile (write, non-destructive, non-idempotent), and the description adds substantial context beyond them: the voting mechanic, 'most can' resolution the evening before, a share link for account-less friends, and the draft/send/off consent behavior. It also discloses guardrails (never invent people, prefer public places, daytime for 13–15).

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?

Purpose and mechanism are front-loaded, and every sentence carries load (voting, share link, consent modes, safety rules). It is a dense single block that is longer than ideal, but nothing is filler.

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 an output schema present, the description need not explain return values, and it covers what an agent needs to call this correctly: the recipients, the option structure, the consent gate, and the naming/safety constraints. Nothing essential is missing.

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 1–9 option count, the gang-OR-friends exclusivity, and the hard rule that names must be the person's real friends/gangs. These constraints go beyond the schema field descriptions.

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 gives a specific verb+resource (propose a meetup, create a 'plan') and scopes it precisely: 1–9 time+place options to ONE gang or to friends by name/@handle. The voting/'most can' flow and share link make it clearly distinguishable from siblings like create_event or add_household_event without opening any schema.

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 supplies strong when-to-use context through the consent model — 'draft' cards to Stream, 'send' creates it now, 'off' refuses — and the 'only with the person's go-ahead' precondition. It does not name explicit alternatives (e.g. create_event for one-off, non-voted events), so it stops short of a full when/when-not/alternatives treatment.

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