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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new context: the search spans all menus site-wide, results are grouped by dish, and each returns price, description, dietary labels, and place URL — important since there is no output schema.

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 purpose, then scope, return shape, and default mode in four tight sentences. The closing "where can I eat X" sentence is slightly redundant with the opening but still aids intent matching.

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 and only two optional params, the description fills the important gaps — what a result contains and what happens when query is omitted — leaving nothing an agent needs in order to call it correctly.

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% with examples, so the schema already documents both query and limit. The description's "omit the query to list the most-served dishes" restates the schema's own note rather than adding syntax or format detail, so baseline 3 applies.

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 ("Find which restaurants serve a dish") plus the search scope (every menu item across all restaurants, grouped by dish), which clearly separates it from siblings like search_places or get_restaurant_menus.

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 an explicit trigger phrase — "Use this for any 'where can I eat X' question" — and explains the no-query mode for listing top dishes. It stops short of naming which sibling to use instead for restaurant-level or place-level lookups.

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