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

Adds genuinely non-obvious behavior beyond the annotations: no invitation email is sent, the operator must share the site link manually, and visitors later sign in with an emailed code. This is exactly the kind of side-effect disclosure that prevents an agent from assuming the tool notifies anyone.

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?

Three short sentences with no waste: capability, precondition, and the surprising non-behavior. Front-loaded and easy to scan.

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 two-parameter mutation tool with an output schema absent, the description covers what happens and what does not. It omits edge cases an agent might hit — duplicate emails, a batch cap, or failure when the sign-in mode is not 'invite' — but nothing critical to a correct call 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 only 50% — 'site' is documented in-schema but 'emails' is not. The description compensates by making clear that emails is a list of addresses added to the guest list, which is more than the bare maxItems/minItems constraints convey.

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: 'Add emails to a site's guest list.' The visitor/member distinction is carried by the resource noun rather than an explicit contrast with invite_member, but an agent can still tell which list is being modified.

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 a concrete precondition — 'needed when visitor_signin is "invite"' — which tells the agent exactly when this tool is required. It stops short of naming alternatives (invite_member, remove_visitor, block_visitor) or when not to use it.

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