Sign the user out. By default signs out of every restaurant; pass a clientId to sign out of one, and an account label to sign out just that account.
| Name | Required | Description | Default |
|---|---|---|---|
| label | No | Account label to sign out, e.g. 'work'. Omit to sign out every account at that restaurant. | |
| clientId | No | clientId of the restaurant to sign out of. Omit to sign out everywhere. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It discloses the main action and the scope nuances, but it does not mention side effects such as token/session invalidation, whether the action can be undone, or whether an active session is required. That is a moderate gap for a no-annotation tool, though the described behavior is still basic and understandable.
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?
A single, front-loaded sentence that states the purpose first and then lists the scope options in order of increasing specificity. Every clause earns its place, and there is no redundant 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 simple logout with only two optional parameters, the description is largely complete: it explains defaults and scoping, and the input schema covers parameter formats. It does not need to explain return values for a logout action, though an explicit note about session invalidation or irreversibility would make it fully complete given the absence of annotations.
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 both parameters and their defaults. The description restates that information in prose and adds the 'every restaurant' default, but it does not meaningfully clarify the ambiguous combined case of passing both clientId and label. Since the schema handles the heavy lifting, 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?
The description opens with the specific verb and resource ('Sign the user out') and then distinguishes the three scopes: all restaurants, one restaurant via clientId, and one account via label. This clearly separates logout from siblings like login, switch_account, and check_order, so an agent knows exactly what this tool does.
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?
The description explains the default behavior and the exact parameter-based conditions for narrowing the scope: omit all params for global logout, pass clientId for a restaurant, pass a label for a single account. It does not explicitly name alternatives like switch_account or state when not to use logout, but the intended usage is clear from the action and the sibling set.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct action and resource: order status vs. order staging vs. order placement, vendor discovery vs. menu retrieval, and login initiation vs. code submission. There is no overlap or ambiguity; even sequential tools like prepare_order and place_order are clearly separated by their purpose.
All tool names follow a consistent verb_noun pattern with lowercase and underscores (e.g., check_order, list_vendors, prepare_order). Even the login and logout tools fit the pattern as single verbs, and there is no mixing of conventions.
With 10 tools, the surface is well-scoped for a restaurant ordering domain. It covers discovery, menu browsing, account management, login flow, order staging, placement, and status checking without feeling bloated or too thin.
The core ordering lifecycle is covered end-to-end (vendor -> menu -> login -> prepare -> place -> check). The only noticeable gaps are the absence of an explicit address-saving tool (though referenced in the login description) and no order cancellation or update capability, though these may be out of scope for typical ordering workflows.
