mcdonalds_menu

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 notes that prices are not available on this surface, calorie labels are often blank, and item IDs/category slugs are market-specific. For a list tool with no annotations, covering data limitations and id scoping goes well beyond the minimum. It does not state pagination or ordering behavior, but the disclosed fields and known constraints are substantial regardless.

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?

Every sentence earns its place. The first sentence states the core action; the middle sentences define the return shape and the necessary input coupling; the final sentences preempt likely mistakes about prices and calorie labeling. There's no filler or repetition. The description is compact yet complete, with the main purpose front-loaded.

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?

Given there is no output schema, the description has to convey what will be returned, and it does so (id, name, URL, image, calorie label). It also covers the main gotchas: market-specific slugs and missing prices. A bit more could be said about pagination, ordering, or what happens when no items match, but for a category-list tool the essentials are covered.

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 100%, so the input schema already documents the fields. The description adds meaningful coupling context: category slugs are not global, they must be paired with the country they come from, and the same country parameter determines item ID scope. This linkage is not explicit in the JSON schema alone, so the prose translates conceptual constraints into parameter semantics.

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 a specific verb and resource: "List one McDonald's menu category's items." It names the return fields (numeric id, name, product page URL, image) and clearly contrasts with related siblings: category slugs feed from mcdonalds/categories and item ids point to mcdonalds_item. An agent can distinguish this from restaurant-menu or item-detail tools without opening other schemas.

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 provides a mini workflow: category slugs come from GET /mcdonalds/categories and must be paired with the country they came from. It explains the market-specific coupling of slugs and item IDs, which is crucial for correct invocation. It doesn't explicitly name alternatives like mcdonalds_restaurant_menu or mcdonalds_item_list, but it implies when the category-level tool is appropriate and how to chain it with the item endpoint.

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