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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: a 24-hour turnaround expectation and an authentication requirement tied to the owner. It does not say whether the request is queued, what happens if the owner is not signed in, or whether the request can be cancelled/duplicated.

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, front-loaded with the action and the alternatives, followed by turnaround and the sign-in precondition. No filler or repeated information.

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, no-output-schema request tool, the definition covers what the tool does, what to expect (24 hours), and what is required (owner sign-in). The one gap is that it never says how to follow up on the request afterward, which the setup_status sibling presumably handles.

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 50%: 'note' is documented in the schema, but the 'what' enum values (cards, channels, white_glove) have no schema descriptions. The description partially compensates by unpacking each choice ('card payments', 'Expedia and Booking.com', 'finish the whole setup by hand'), which is enough for an agent to pick the right value. With half the parameters covered by the schema, a 3 is the appropriate baseline.

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?

The description gives a specific verb and resource: it asks the human Guest Logic team to perform a connection on the owner's behalf. The three enumerated outcomes (card payments, Expedia/Booking.com channels, full hand-held setup) map cleanly onto the tool's intent and distinguish it from self-serve siblings like start_signup or setup_status, though it never names those siblings.

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?

Usage context is clear: this is the escalation path when connections must be made by the team or finished manually, and 'Needs the owner's sign-in' signals a real precondition before invoking. It stops short of explicit exclusions (e.g. 'do not use if setup_status shows already connected'), so the agent must infer the boundary itself.

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