arbys_menu

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

No annotations are present, so the description carries the full behavioral burden. It goes beyond a simple 'list' by disclosing the price conditionality, the default catalog's absence of pricing, the price-of-exactly-0 edge case, and the permanent passthrough nature of store_id. It does not mention pagination or errors, but for a one-category menu read the relevant behavior is well covered.

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?

The purpose is front-loaded and the prose is dense with useful information. There is minor redundancy between the first sentence ('List... items') and the second ('Returns the items...'), and the nutrition field list is long, but each sentence earns its place by adding semantics or caveats. It is appropriately sized for a tool with two parameters and nuanced store_id behavior.

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?

Despite having no output schema and no annotations, the description covers the tool's purpose, both parameters, the source of category slugs, store_id semantics, the price edge case, and the exact item fields returned. An agent can select and invoke this tool correctly without consulting external documentation; the only omissions are generic concerns like pagination and error handling, which are not essential here.

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%, but the description adds substantial meaning beyond the schema: store_id defaults to 0, refers to Arby's priceless national catalog, must be passed as a known value, cannot be looked up, and only yields prices when the store resolves to a priced catalog. It also reinforces that category must be a slug from /arbys/categories. An agent can confidently construct valid calls with this context.

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 uses a specific verb and resource: 'List one Arby's menu category's items with full nutrition and price.' It distinguishes itself from category/list/location siblings by emphasizing 'one category' and by noting that store_id is a passthrough value, not a resolvable location. The return contents are also enumerated, so an agent knows exactly what this tool produces.

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?

It explicitly tells the agent where to get category slugs ('Category slugs come from GET /arbys/categories'), when to pass a store_id ('pass a store_id you already know to get that store's pricing'), and what not to attempt ('there is no location-lookup endpoint in this family'). This gives clear when/when-not guidance and effectively distinguishes the tool from arbys_categories and arbys_locations.

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