kroger_search

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

With no annotations, the description carries the full behavioral burden and does so excellently: it discloses the JSON-API primary path, the rendered-page fallback, the `source` field that reports which path answered, real upstream pagination, and the critical caveat that facet/sort usage disables silent fallback. These are exactly the non-obvious behaviors an agent needs to know.

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 front-loads the core search behavior and then packs each remaining sentence with non-redundant operational detail: returned fields, facets, fallback path, and error behavior. The opening summary sentence is a minor repetition, but the overall density earns the high score.

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 an 11-parameter search tool with no output schema and no annotations, this description covers everything an agent needs to call it correctly: return shape, facet behavior, pagination, fallback semantics, and failure mode. The schema already documents parameter details, so nothing critical is missing.

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 baseline is 3; the description adds meaning by grouping the filter parameters into facet categories (brands, nutrition, savings, price range) and explaining that filter/sort parameters only apply to the JSON path, which is not in the schema. Per-parameter syntax is already well covered by the schema.

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 verb and resource ('Search Kroger products') and immediately narrows the operation to keyword search returning normalized product cards (price, unit price, brand, size, stock level) plus facet groups. That distinctive return shape separates it from sibling product-detail, category, and suggest tools even without naming them.

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 clear context: this is the keyword-search entry point for Kroger products, and filters/sort are available. It does not explicitly route away from siblings like kroger_products, kroger_category, or kroger_suggest, so it stops short of full alternative guidance, but the usage context is unambiguous.

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