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

Annotations already mark it read-only/idempotent, and the description adds important behavior beyond that: offline checksum validation, the likelihood of no product hit for non-food codes, and operational constraints such as $0.01 per call, the prepaid x-credit-token header, free daily allowance, and no wallet/API key requirement.

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 core behavior is front-loaded in the first clause, followed by a useful limitation and then pricing/auth details. Four sentences carry distinct pieces of information without redundancy, though the 'product hit' phrasing is slightly telegraphic.

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?

With only one parameter and an output schema present, the description covers purpose, applicable product domain, likely failure mode, cost, auth path, and free tier. An agent has enough context to decide to invoke the tool and understand its read-only, bounded behavior without needing return-value detail.

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 already documents the sole required 'code' with description 'Barcode digits,' and schema coverage is 100%. The tool description reinforces this with UPC/EAN/GTIN and checksum context, but doesn't add substantial parameter-level syntax or constraints beyond what the schema provides.

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?

Description begins with 'Checksum + Open Food Facts product hit' and clearly states the tool validates UPC/EAN/GTIN checksums offline and looks up food/consumer items. This gives a specific verb-resource pairing and sufficiently distinguishes it from the large sibling set, none of which are barcode-focused.

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 states the lookup applies 'when it is a food/consumer item' and warns that 'non-food codes often checksum-ok with no product match,' setting clear expectations. It does not explicitly name sibling alternatives or a strict when-not-to-use rule, but the context makes appropriate usage inferable.

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