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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower. The description still adds real value beyond them: anonymous logging of zero-result queries (a privacy-relevant side effect), discontinued items being included and listed last so total can exceed list_chains' count, and nutrient-only-for-publishing-chains constraint. It does not cover rate limits or pagination limits beyond offset caps, which keeps it from a 5.

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 purpose, then query semantics, then filter/ordering rules and return hints. Dense and nearly every clause carries information, but it reads as one long run-on block and repeats ordering rules that also appear in the sort parameter description.

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 9-param search tool with no output schema, the description covers matching behavior, ordering, pagination caveat (total vs item_count), and what each result contains (id, page url, source_file). An agent can invoke it correctly and interpret results without further documentation.

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 44%, but the description compensates heavily: it explains query matching scope (item name, size, category, genre, chain name), AND semantics for spaces, kana/width normalization, nickname support, and nutrient meaning plus sort defaults. Gaps remain for limit/offset/min_kcal/max_kcal, which are undocumented in both schema and description.

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 (search) and resource (menu items with nutrition facts) and scopes it to Japanese chains/stores and packaged foods. It also names the sibling relationships explicitly (id for sum_items, comparison with list_chains' item_count), so an agent can distinguish it from siblings without opening another schema.

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?

Gives concrete when-to-use guidance: combine free-text query with chain/genre/kcal filters, use nutrient only for nutrient-rich lookups on chains that publish it, and describes the default ordering rules per filter combination. It also explains what happens with zero-result queries, which is actionable behavior an agent should know before calling.

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