culvers_menu

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

With no annotations, the description carries the full burden. It discloses what is returned (name, description, image, nutrition link), notably explains that prices are not available on the national catalog and why, and says no credential-free per-restaurant pricing source was found. It doesn't mention read-only or errors, but for a list operation the transparency is sufficient.

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 description is three sentences. The purpose is front-loaded, followed by the return structure, then a caveat about prices and an alternative. The third sentence is a bit long but saves the caller from expecting prices or missing the modifier pointer. Overall, it's purposeful and well ordered.

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 single-parameter tool with no output schema and no other context, the description covers the category source, the return items and their fields, and a predictable limitation (no prices). It doesn't specify the exact response format or pagination, but the core information an agent needs to call the tool and evaluate the result is present.

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%: the parameter 'category' has a description in the schema. The description repeats the same source ('Category slugs come from GET /culvers/categories') and adds slight context about it being one category. This matches the baseline of 3, as it doesn't add deeper semantics, but the schema already covers it.

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 states a specific action and resource: 'List one Culver's menu category's items.' It also names the return fields and differentiates from related tools: slugs come from culvers_categories, and full modifier/topping detail is in culvers_item. This clearly tells an agent what the tool does and how it relates to similar siblings.

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 gives the prerequisite that category slugs come from culvers_categories and explicitly points to culvers_item when full modifier/topping detail is needed. It does not say 'use this tool when' in plain words, but the purpose sentence implies it, and the pointer to an alternative is helpful. This is clear enough context without explicit exclusions.

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