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

Annotations only cover safety (readOnly, idempotent, non-destructive, closed-world); the description adds substantial behavior beyond them: chain items resolve to published chain figures by country, unmatched chain items silently fall back to USDA with the 'say' line disclosing it, unpublished chain weights yield amount.grams=null and null per_100 values, and meals return items plus total. This is exactly the kind of edge-case disclosure that prevents wrong expectations.

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 purpose and routing guidance are front-loaded in the first two sentences, and nearly every clause carries distinct information (data sources, chain behavior, fallback, return shape). The example enumerations are dense and slightly overstuffed, which keeps it from a 5.

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 carries the full burden and does: it enumerates the returned fields (nutrition for the amount, per_100 values, portions, UK traffic lights per 100 g or 100 ml for drinks, caffeine_mg), the chain object shape, and the meal items/total structure. An agent can set expectations completely without guessing.

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 baseline is 3, but the description goes further by explaining the interplay of q, grams and servings ('put the whole amount and food in q, or pass grams or servings separately') and how country selects UK vs US chain figures (GB and IE get UK). That is real disambiguation beyond the schema text.

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 ('calories and macros for a food, dish or product') scoped to the amount the user says, and the examples make the domain unmistakable. It never names the siblings get_barcode_nutrition or get_meal_ideas to draw the boundary explicitly, so an agent must infer that barcode lookups and meal planning live elsewhere.

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?

Rich usage context: it shows the phrasing patterns the tool expects ('how many calories in a Big Mac?', 'protein in 200g chicken breast', meals like '2 eggs, 2 slices of toast and a coffee') and tells the agent to either put everything in q or split grams/servings. There is no explicit when-not-to-use or named alternative, so it stops short of a 5.

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