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

Annotations already cover safety (readOnly, non-destructive, open-world), and the description adds real context beyond them: the upstream data sources, that the barcode path yields extra data (ingredients, allergens, Nutri-Score) while the name path does not, and that recall reporting is conditional on a known brand. It stops short of describing failure behavior for unmatched barcodes/names or partial data.

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?

Front-loaded with the core capability and its two input paths; every sentence contributes (nutrient list, barcode extras, recall condition, usage scope). It is dense as a single run-on paragraph, and the long nutrient enumeration could be trimmed or tabulated, but there is no filler.

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 no output schema, the description does the heavy lifting of describing return values and does so thoroughly (per 100 g / per serving / custom grams, %DV, ingredients, allergens, Nutri-Score, recalls). What's missing is guidance on supplying zero arguments (no required params) and what is returned when lookup fails.

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 description coverage is 100%, so the schema already documents query, fdc_id, barcode, and amount_g. The description only adds marginal semantics — that values are scaled 'for any amount in grams' and that barcode input unlocks ingredients/allergens. Critically, it never clarifies the one-of input model (query vs barcode vs fdc_id) despite zero required parameters.

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 concrete verb and resource ('Nutrition facts for a food') plus the two lookup paths (barcode via Open Food Facts, name via USDA FoodData Central) and enumerates the returned fields. This clearly separates it from siblings like check_recalls, search_products, or compare_prices, which do not return per-food nutrient panels.

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?

Explicitly names the use cases — 'what's in a food, comparing foods, or whether a packaged food was recalled' — and adds a scope boundary ('Not medical or diet advice'). It does not, however, route the agent elsewhere for pure recall lookups (check_recalls) or packaged-product searches (search_products), so the alternative-selection guidance is incomplete.

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