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

With no annotations, the description carries the disclosure burden. It explains the two-step browser flow, that a URL is returned, that the user must open it, and that a code must be copied and passed to submit_login_code. It stops short of describing session/expiry behavior or potential errors, so it is not a 5, but it is substantially transparent.

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 sentences, each earning its place: the purpose, when it is and is not needed, and the exact multi-step protocol. The most important scoping constraints are front-loaded, and there is no filler.

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 multi-step authentication flow with no output schema, the description explains the returned URL, the external browser interaction, the code extraction, the next sibling to call, and the per-restaurant constraint. Minor gaps remain around expiration, errors, and what happens on repeated calls, but an agent has enough to invoke it correctly.

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?

The schema already documents clientId with meaningful context, and the description does not add parameter-specific detail. However, the description's per-restaurant note reinforces why clientId matters. With 100% schema coverage, baseline 3 is appropriate.

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 action ('Start signing the user in'), the resource (a restaurant), and the overall goal (place orders). Clearly distinguishes itself from the sibling submit_login_code by positioning this as the first step that returns a URL, and notes that browsing the menu never requires it.

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 says when login is needed ('only ordering and saving an address do'), when it is not needed ('Browsing the menu never needs this'), and gives the follow-up step ('you call submit_login_code'). It also warns that login is per restaurant, which prevents a common misuse.

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