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

Goes well beyond the annotations: discloses the preview-then-confirm workflow, that previewHash must accompany preview=false, that changes force re-confirmation, that 'note' is operator-only and never sent, and that the page itself re-verifies the phone number. None of this is captured by readOnlyHint/openWorldHint/idempotentHint, and it is exactly the extra behavioral context an agent needs.

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-loads the permission precondition in brackets, then the action, then caveats, then the confirm workflow – a logical order despite dense punctuation. Every clause carries information, though the single run-on structure makes it slower to parse than necessary.

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 five-param, non-idempotent mutation with no output schema, the description covers permission, non-delivery semantics, phone verification and the preview/confirm contract well. It stops short of saying what preview returns or what the prepared link/invitation object looks like, which is the remaining gap given 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 description coverage is 0%, so the description carries the burden, and it does clarify three of five params: note (instructions only, unsent), preview (defaults to preview) and previewHash (paired with preview=false). activityRef and userId are only implied by 'specified cloud member' and 'this event', with no format or constraint guidance, so the coverage remains partial.

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: grant the named audience to a specified cloud member and prepare a self-fill link, explicitly 'not sending on their behalf' and 'not representing acceptance'. This contrasts it in spirit with send_guest_invite_now and the invite-link creators, though it never names those siblings outright. Clear enough to distinguish its manual, no-send action from the automated alternatives.

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?

Leads with the precondition ('requires current contact management rights or valid event authorization') and spells out the confirm flow (default preview; on confirmation, resend same params plus previewHash with preview=false; re-confirm on any change). It does not explicitly name which sibling to use instead, so it falls short of full routing guidance.

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