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

Goes well beyond the annotations: emails are sent from the account, the operation is all-or-nothing (one bad address or over-limit list adds nobody), it requires a plan with private sharing, and it does not itself make the site private. This is rich behavioral context annotations do not carry.

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-loaded with the core action, then dense but purposeful clauses. Every sentence carries information, though the multi-clause structure is slightly compressed.

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 and annotations covering safety/idempotency, the description fills the remaining gaps: prerequisites (private-sharing plan), atomicity, and the privacy distinction. Nothing an agent needs 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 description coverage is 100%, so the schema already documents `role`, `site`, and `emails`. The description restates the `comment` effect and email sourcing, adding marginal value over structured fields. Baseline 3 applies.

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: adds email addresses to a site's list and sends invitations. Clearly distinguishable from siblings like remove_person, list_people, and update_site.

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?

Explicitly constrains input ('use only addresses the person gave you — never guess, infer or look one up') and routes the privacy decision to the alternative: 'Inviting does not make the site private; update_site's `invitedOnly: true` does.'

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