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), so the description is free to add real behavioral context: no-result queries are logged anonymously for chain-coverage decisions, default ordering depends on whether a query is present, and matching is kana/width-insensitive with nickname support. These are traits an agent could not infer from the annotations.

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?

It is a dense single paragraph, but the purpose leads and each subsequent clause carries distinct information (matching rules, filter combinations, sort behavior, return fields). No sentence is pure filler, though the query-matching details make it heavier than ideal for a one-glance scan.

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, the description correctly compensates by naming the returned fields (item id for sum_items, page url, source_file). For a 9-parameter, zero-required search tool this is close to complete; only pagination (limit/offset) and empty-result behavior beyond the logging note are unaddressed.

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 only 33%, so the description must carry weight and it does: query matching rules (AND on spaces, katakana/hiragana and full/half-width equivalence, nicknames like ケンタ/マック/サイゼ), sort semantics for relevance vs kcal, and nutrient scoping are all explained. Only limit/offset pagination behavior is left undocumented.

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 first sentence names a specific verb (Search) and resource (menu items of Japanese restaurant chains) and adds the payoff (nutrition facts), which no sibling provides. It is immediately distinguishable from list_chains (enumeration), sum_items (aggregation) and request_missing (data requests).

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 tells the agent how to combine filters ('Combine with chain / genre / kcal range') and when the nutrient parameter is appropriate ('Use nutrient to find items rich in a nutrient (only chains that publish it)'). It also routes to sum_items via the item id, but never states when to prefer list_chains or request_missing, so there is no explicit exclusion.

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