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

Goes well past the annotations by disclosing data provenance (USDA for generic, Open Food Facts for brands, chain-published figures for chain items), the country-based region selection, the chain object shape, and the null-weight/null-per_100 fallback when a chain doesn't publish a weight. That is exactly the behavioral detail annotations cannot carry.

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 purpose and examples, then proceeds to provenance and returns. It is long and occasionally repetitive (chain items get several clause repeats), but nearly every sentence adds distinct information an agent would need.

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 and only safety annotations, the description fully carries the return contract: nutrition for the amount, per_100 values, portions, UK traffic lights, caffeine_mg, chain object, and meal-level items plus total. Nothing an agent needs to call or interpret it is missing.

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 baseline is 3, but the description adds real guidance beyond it: how q, grams and servings relate ('put the whole amount and food in q, or pass grams or servings separately') and that portions like slice/cup/small/medium are recognized. Minor gaps remain on the country default behavior, which is left to the schema.

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+resource ('calories and macros for a food, dish or product, for the amount the user says') and pins the scope to a named amount. It is clearly distinguishable from the sibling platepal_get_barcode_nutrition, which is barcode-driven rather than query-driven.

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?

Offers a rich set of trigger examples ('how many calories in a Big Mac?', 'protein in 200g chicken breast') and explains both input modes (whole amount in q vs. grams/servings separately). It does not explicitly exclude or route away from the barcode sibling, so it stops short of 5.

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