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

Annotations already flag destructiveHint=true, openWorldHint=true, and idempotentHint=false, and the description adds real operational context beyond them: it counts against a weekly invite limit, sends real emails/push, is host-only, and dry_run previews counts and blockers. These are exactly the behavioral traits (rate limit, side effects, authorization, safe-preview escape hatch) an agent needs before invoking a destructive send.

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?

Dense but well front-loaded: identity, targets, options, behavior, routing, then the dry_run escape hatch. Every clause carries information, though the single packed paragraph could be trimmed marginally for scanability.

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 destructive, ten-parameter mutation with no output schema, the description covers side effects, rate limits, authorization, the preview path, and sibling routing. Nothing an agent needs to call it correctly 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 0%, so the description carries the full burden, and it maps nearly all ten parameters to their roles (recipient_uids=people, distribution_list_ids=saved lists, external_contacts=manual contacts, attach_promo_code, custom_message, send_as_community_id=linked community, scheduled_start_at=schedule, dry_run). It stops short of format details (e.g. the expected format of scheduled_start_at or delivery_method defaults), so it is strong but not complete.

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 (send invitations), the resource (a live event), and the delivery scope (app, email, or both) in the first clause. It explicitly distinguishes itself from the two nearest siblings, make_announcement and send_email_campaign, so an agent can route 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?

Gives explicit when-to-use ('NEW people to one event') and when-not-to-use conditions, naming make_announcement for existing guests and send_email_campaign for lists/newsletters. This is the full when/when-not/alternatives pattern.

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