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

With no annotations, the description carries the burden, and it does disclose the credit cost and the shape of returned data, including that nutrition is normalised per 100g. It omits what happens for an unknown barcode (error vs empty result), geographic/product coverage, and whether results are cached or rate limited.

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?

One compact sentence front-loads the resource and key, then lists return fields and the cost in parentheses. No filler, no repetition of the tool name.

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 one-parameter lookup with no output schema, the enumeration of return fields plus the per-100g basis and credit cost is nearly sufficient. The remaining gap is edge-case behaviour on invalid or unknown barcodes, which an agent would need to handle gracefully.

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 single 'barcode' parameter is formally documented, and the description adds the meaning that it identifies a food product. It does not specify accepted barcode formats (EAN-13, UPC-A) or whether the check digit is required, which is the one detail an agent could actually get wrong here.

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 names the resource (a food product) and the lookup key (barcode), then enumerates the returned fields (name, brand, ingredients, allergens, Nutri-Score, nutrition per 100g). That is specific enough to separate it from siblings like product_recalls or food_alerts, though the verb ('look up') is only implied.

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?

Usage is implied by the barcode key, and the '(cost: 1 credit)' note gives a real decision input for an agent weighing calls. However, it never states when to prefer this over related tools such as product_recalls or food_alerts, nor any precondition (e.g., needing an EAN/UPC code in hand).

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