chipotle_menu_metadata

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It clearly indicates a read-only operation ('Get', 'Returns') and notes the lack of prices, which is a limitation. However, it does not mention any other behavioral aspects such as pagination, rate limits, authentication requirements, or the scale of the response. For a metadata endpoint, this might be sufficient, but the absence of explicit safety or performance notes is a gap.

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 moderately long but well-structured. It opens with the purpose, then breaks down the content areas (categories, items, sections, dietary tags) with examples, and closes with a cross-reference for prices. Each sentence adds meaningful detail without redundancy. It is not excessively verbose and is easy to parse, though it could be tightened slightly.

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?

The description does a strong job of explaining the returned data structure given there is no output schema. It covers categories, items, customization sections, dietary tags, and how to obtain prices via joins. It lacks mention of potential pagination, size limits, or whether all data is returned in one call, but for a metadata endpoint the description is fairly complete for an agent to understand what to expect and how to use it.

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 input schema provides 100% coverage, with both parameters (region and channel) having descriptions and enums. The description does not add any additional meaning about how these parameters affect the returned data—it doesn't explain, for example, that different regions might have different menu items or that channel affects which presentation metadata is relevant. Since the schema already covers the basics, the description adds no extra value beyond the schema, so a baseline of 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 clearly states the tool returns 'Chipotle's menu presentation metadata' and elaborates on what that includes: categories, items, sections, groups, and dietary tags. It also distinguishes itself from other endpoints by claiming it carries data 'no other Chipotle endpoint carries' and explicitly notes it lacks prices, pointing to specific join targets. This gives an agent a precise understanding of the tool's purpose and differentiates it from siblings like chipotle_menu or chipotle_restaurant_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?

The description implies usage by explaining what data it provides and what it doesn't (prices), and suggests joining against /chipotle/menu or /chipotle/restaurant/menu for prices. However, it does not explicitly state when to prefer this tool over alternatives like chipotle_ingredients or chipotle_meals. The guidance is mostly about what not to expect and how to get missing data, which is useful but not fully explicit about selection criteria.

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