instacart_departments

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

With no annotations, the description carries the full burden of behavioral disclosure. It meaningfully states the tool is metadata-only, does not return products, and that the data is public from Instacart's storefront navigation. This goes beyond a simple 'get' by setting clear expectations, though it does not address authentication, rate limits, or error behavior.

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 efficiently structured in four sentences, each contributing unique value: the action, the return structure, exclusions, and data source. It is front-loaded with the verb phrase and contains no filler or redundancy.

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 simple taxonomy tool with no output schema, the description adequately covers the return value (two-level taxonomy), the scope (metadata only), and the source (public Instacart storefront). It is complete enough for an agent to understand what it will receive, though a more explicit description of the response format (e.g., array of departments) would make it fully complete.

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 descriptive parameter explanations (e.g., shop_id is 'Store's opaque shop id, from GET /instacart/stores'). The description does not add additional parameter-level detail beyond what the schema already contains, so it meets the baseline without enhancing 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 clearly states the tool gets the Instacart store department taxonomy, specifies it returns a two-level taxonomy (department and subcategory), and provides examples like Produce and Dairy & Eggs. It explicitly differentiates from sibling tools by noting it is 'Metadata only, does not return products,' distinguishing it from instacart_search and instacart_item.

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 when a store's departmental structure is needed and effectively excludes product-related use cases with 'does not return products.' However, it does not explicitly name alternative tools such as instacart_search or instacart_item, so it provides strong context but stops short of explicit when-not/alternative guidance.

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