Look up a product by UPC/EAN. Returns found=false when unknown. Does not search recalls.
| Name | Required | Description | Default |
|---|---|---|---|
| upc | Yes | UPC or EAN barcode digits |
| Name | Required | Description | Default |
|---|---|---|---|
| upc | Yes | ||
| hint | No | ||
| found | Yes | ||
| product | No | ||
| branded_food | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds concrete behavioral detail beyond annotations by specifying 'Returns found=false when unknown.' This tells the agent that unknown products resolve to a false flag rather than an error or empty result. It also reinforces the open-world behavior implied by the openWorldHint.
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?
Two sentences with no filler. The primary action is first, the return behavior is second, and the non-recall scope is stated clearly. Every sentence earns its place.
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?
This is a simple one-parameter lookup with a fully documented schema, an output schema, and annotations covering read-only, open-world, idempotent, and non-destructive behavior. The description adds the only missing behavioral nuance: the 'found=false' response for unknown products.
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 schema already fully documents the 'upc' parameter as 'UPC or EAN barcode digits' with 100% coverage. The description merely paraphrases this ('by UPC/EAN') and adds no new parameter-level meaning, so the baseline of 3 is appropriate.
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?
States a specific verb and resource: 'Look up a product by UPC/EAN.' It clearly differentiates from recall-related siblings by saying 'Does not search recalls,' so an agent knows this is for product lookup, not recall information.
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 a clear exclusion: 'Does not search recalls,' which tells the agent when not to use this tool. However, it does not explicitly name the alternative recall tools, so it stops short of providing full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct roles, and the descriptions explicitly separate product lookup from recall search. However, the multiple recall search entry points (by query, UPC, image, and identifier) overlap enough that an agent could pick the wrong one without carefully reading the details.
Tool names consistently follow a snake_case verb_noun pattern such as add_, list_, remove_, search_, get_, create_, revoke_, and mark_. The single-word signup is the only minor deviation, but it does not undermine the overall naming system.
At 19 tools, the set is in the borderline-heavy range. The count is justified by the multiple subdomains like API key management, inventory, watch patterns, notifications, and recall searching, but it still feels slightly above the ideal well-scoped tool surface.
Core recall search, product lookup, inventory tracking, watch pattern management, notifications, and API key lifecycle are all covered well. Minor gaps exist such as no way to update a watch pattern or view account usage limits, but agents can generally work around them.