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

No annotations exist, so the description carries the full burden, and it does disclose meaningful behavior: compact results with key nutrients, cross-source deduplication of the same food from USDA/CIQUAL, market-preferred version selection, and a `variants` collection where each version carries only its own source's values. That is genuinely useful. However, pagination is never mentioned despite a `cursor` parameter, and there is no statement about the result cap, ordering, or what happens when no market match exists.

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 the core action and modes, then the return shape, then the deduplication rule — a sensible priority order. The final sentence is dense but every clause carries non-obvious behavior (market preference, variants, per-source values), so little could be cut without losing information.

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?

For a six-parameter search with no output schema, the description does the essential work of describing what comes back (compact hits, key nutrients, variants). The one substantive hole is pagination: with a `cursor` parameter and a `limit` ceiling of 50, an agent cannot tell from the definition how to retrieve further results.

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 description coverage is only 17%, so the description must compensate. It covers the important ones — `query` (name in any language / barcode / semantic), `kinds`, `brand`, `market` — but adds no detail on `limit` (default 10, max 50) and says nothing at all about `cursor`, leaving pagination semantics entirely undocumented in both schema and prose.

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?

"Find entities by name in any language, by barcode, or semantically" states a specific verb plus the three matching modes, and the closing sentence explains the merged-result shape. It cleanly separates itself from `get` ("call get for full cards") but never distinguishes itself from the sibling `lookup_barcode`, even though it claims barcode search as a mode — a real overlap left unresolved.

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 one explicit routing rule — use this for compact hits, use `get` for full cards — which is the main decision an agent faces. It stops short of when-not guidance: no direction on when to prefer `lookup_barcode` over the barcode mode here, and no advice on choosing `kinds` values or when to page with `cursor`.

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