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

With no annotations, the description carries the full burden and does well: it discloses that results are currently-valid offers only, that they are ordered cheapest first, and critically that self-serve keys see published campaign offers but not everyday shelf prices, which are Salling-only and restricted to partner keys. This is exactly the kind of auth/plan-scoping context an agent needs. It doesn't cover pagination behavior beyond the schema's limit, nor what happens on empty results or invalid identifiers.

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?

Three sentences, front-loaded with the question the tool answers, then the composition pattern with get_stores, then the access caveat. Every sentence earns its place. The first sentence is dense with several ideas packed around a colon, which slightly hurts scannability but not enough to call it verbose.

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?

No output schema exists, and the description compensates by sketching the return shape -- offers for one product, cheapest first, chain slug and name resolved -- plus the key access restriction. The main gap is that required_parameters is 0 in the schema, yet the tool clearly needs either ean or product_id; the description never says so, leaving an agent able to call it with neither.

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 all three parameters are already documented (EAN-13 pattern, UUID product id, 1-50 limit with default 20). The description only restates that the product is identified 'by EAN or product id,' adding little beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 -- return currently-valid offers for one product, cheapest first, with chain slug and name resolved -- and frames it as answering 'where is this product cheapest right now?'. It implicitly distinguishes itself from search_catalog_offers through the cheapest-first ordering and single-product scope, but never names the sibling directly.

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 gives concrete usage context: use it for a single product's cheapest offer, then combine with get_stores(lat/lng, chain_slug) to find the nearest store carrying the winning chain. It also states the data-visibility constraint for self-serve keys. What's missing is an explicit exclusion -- e.g. 'use search_catalog_offers instead when you want to browse offers across products' -- and a note that at least one of ean/product_id must be supplied.

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