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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds substantial behavior: it REFUSES non-raw input, warns that the 30 reconciled tables disagree by a median of 1.96x, and states it does not select a qualifying table. It does not describe pagination or latency, but for a screening tool this is strong disclosure.

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 scope and the NOT-valid exclusion, with a clear screening-only qualifier at the end. It is long, and the raw/preparation reasoning partly restates the schema's own parameter description, so a few sentences do not fully earn their 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?

No output schema exists, so the description must carry the return contract, and it does: results list the tables that do and do not support each claim and the tool does not pick a qualifying table. Combined with the scope and refusal rules, an agent has everything needed to call it correctly.

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, and the schema already documents every parameter in detail. The description adds genuine meaning on top: the market default is justified ("the divergence is usually the point"), which tells the agent why 'both' matters rather than just what it does.

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?

The description states a specific verb and resource (report which nutrition claims the published data supports) and immediately scopes it to GB/EU and US rules with concrete thresholds. It is unmistakably distinct from every sibling (lookup_food, nutrient_ranking, search_foods), none of which evaluate legal claim thresholds.

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 gives explicit when-to-use (raw or minimally-processed whole food, unfortified single-ingredient flour) and when-not (cooked, juiced, or manufactured products), and instructs the agent not to call it in those cases. The screening-only caveat under Art. 5(1)(b)(i) further bounds what the result means.

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