List nutrition fields

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description instead adds genuine domain behavior — that a constraint excludes dishes publishing no value for that nutrient, and that 'trace' or '< 1%' means missing rather than zero. That is exactly the kind of non-obvious semantics annotations cannot convey. It stops short of describing response ordering or cache/staleness behavior, keeping it at 4.

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?

Three sentences, front-loaded with the actual list contents, zero filler. The closing sortFields sentence is somewhat displaced — it describes a parameter of a different tool — but it is compact and earns its place as domain context.

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 an output schema present, return values need no explanation, and the description supplies the interpretive layer an agent needs: what the identifiers mean, how units and Daily Value baselines relate, and how absent/trace values behave. Only the explicit 'call this first' workflow link to filter_dishes 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?

Zero parameters, so the baseline is 4; the schema is empty and closed. The description does add meaning about fields consumed elsewhere (alternative threshold units, sortFields including servingSize and mhealthyTier with 'a:b' ratio syntax), which is useful even though none of it belongs to this tool's own input.

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?

Opens with a specific verb and resource — 'List the canonical nutrient identifiers, their units, the alternative units a threshold may be written in, and the Daily Value basis' — which is far more precise than the title. It is clearly a reference/metadata lookup, distinguishable in kind from get_item_nutrition, though it never names a sibling to make the contrast explicit.

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?

Usage is only implied: an agent can infer this is the discovery step before writing a nutrient constraint or a sortFields expression. There is no explicit 'use this before calling filter_dishes' statement and no when-not guidance, so the routing must be reconstructed from the constraint and sortFields remarks.

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