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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description goes well beyond them by disclosing the data provenance model — up to 30 tables, per-source contribution counts, and per-source spread — which tells the agent the values are citable and not asserted, plus the 132-nutrient plus 66 research-tier breadth.

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 core capability, then the differentiator, then accepted input formats — efficient and well ordered. Minor redundancy: 'Covers Indian foods from IFCT 2017 (ICMR–NIN, India)' restates IFCT India already named in the source list.

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 only two parameters, no output schema, and rich annotations, the description is nearly sufficient: it explains what comes back (full nutrient profile with source attribution) and what inputs work. It omits behavior for ambiguous names and whether a partial-match returns one record or several, which would matter for a lookup tool without an output schema.

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 a baseline of 3 applies. The description adds real meaning beyond the schema's terse 'Food slug, common name, or regional alias' by giving concrete alias examples ('karela', 'chickoo') and the slug form ('bitter-gourd'), which clarifies the fuzzy-match behavior the agent should expect. The optional nutrients filter 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 and resource: 'Get the full per-100 g nutrient profile of a whole plant food,' with the distinguishing trait of multi-source reconciliation. It contrasts itself with 'a single-source table' rather than naming sibling tools like search_foods, so the differentiation is topical rather than tool-directed.

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 implied (look up a food you can name to get its nutrient profile) but there is no explicit when-to-use versus search_foods, no note on what to do if the name is ambiguous, and no stated exclusions. The accepted-input sentence is helpful context but not routing guidance.

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