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

Annotations already declare readOnlyHint, idempotentHint and a closed world, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: the menu reflects what is available today (time-sensitive data), and names are returned in the restaurant's own language, which tells the agent not to expect English labels or to attempt translation.

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?

One sentence that front-loads the resource and then lists the payload contents, plus a short clause on language. Nothing is redundant and nothing important is buried.

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 one required parameter, no output schema and a fully documented schema, the description does enough: it sets expectations for what fields come back and warns about localized names. It could say more about failure modes or whether menus can be empty, but nothing critical 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?

The single restaurant_id parameter is fully documented in the schema, including UUID format and the hint to obtain it from find_restaurants, so the description needs to add little. It says nothing extra about the parameter, which is appropriate at 100% schema coverage. 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 resource (a Foodly restaurant's menu) and enumerates its contents: sections, dishes, drinks, prices, sizes, allergens. An agent can immediately tell this is a menu-fetch tool. It stops short of explicitly contrasting itself with the sibling get_restaurant, which likely returns venue details rather than the menu.

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 is only implied: you need a restaurant, and the schema points to find_restaurants for the id. There is no explicit statement of when to call this rather than get_restaurant, nor any note about what to do when a menu is unavailable (e.g. restaurant closed or menu not published).

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