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

Annotations establish the mutation/safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds the key behavioral fact that the output is 'local ephemeral' and never transmitted, so no external side effect occurs. It omits idempotency semantics, which the annotation only flags without explaining.

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?

Two sentences, front-loaded with the action and its scope, and no redundant text. Every clause earns its place.

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, return values need no explanation, and all five parameters are schema-documented with annotations covering safety. The description is largely complete; the lifecycle of the 'ephemeral candidate' (expiry, reuse) is the only lightly covered aspect.

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 100%, so the schema already documents target, agentId, message, permissionBasis and operatorOrganizationIdentifier. The description only restates target/permission concepts ('HTTPS machine endpoint or opt-in recipient') without adding syntax or format detail beyond the schema.

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+resource ('Create... invitation candidate') and immediately scopes it as 'local ephemeral' versus an actual send. The negation 'It does not send the invitation' sharply distinguishes it from outbound/send siblings, though no sibling is named explicitly.

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?

Implies valid usage via 'for a documented HTTPS machine endpoint or opt-in recipient', which maps to the permissionBasis enum, but gives no explicit when-to-use vs. alternatives (e.g., outbound_gateway_policy) or exclusions beyond the no-send caveat.

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