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

No annotations are present, so the description carries the full burden. It discloses that the search covers 'every menu item across all restaurants' and that results are grouped by dish, returning price, description, dietary labels, and place URL. It also mentions the omit-query behavior. Minor gaps include not specifying result ordering or potential error cases, but overall it is quite transparent.

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?

The description is two sentences plus an example, tightly structured and front-loaded. Every sentence contributes: the first defines the core purpose, the second provides usage detail and output expectations, and the example is illustrative. No redundant or extraneous text.

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?

This is a relatively simple search tool with two optional parameters and no output schema. The description fully covers its behavior, including the search scope, grouping, returned fields, and alternate mode (top dishes). It gives enough context for an agent to invoke it correctly and interpret results, making it complete for its complexity.

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?

The schema already documents both parameters well (100% coverage), including the omit behavior for query. The description adds meaning by explaining the search scope and what each result contains, e.g., 'returns each restaurant serving it with price, description, dietary labels, and the place URL.' This contextualizes how the query parameter is used beyond mere syntax, justifying a score above the baseline.

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 description clearly states the tool's function: 'Find which restaurants serve a dish in this neighborhood.' It uses a specific verb and resource, and distinguishes itself from sibling tools like search_places and get_restaurant_menus by focusing on dish-level search across all restaurant menus. The example with 'feijoada' further clarifies its purpose.

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?

Explicit guidance is given: 'Use this for any "where can I eat X" question.' This tells the agent exactly when to use the tool. It also explains the conditional behavior of omitting the query to list the most-served dishes, providing a clear alternative invocation pattern.

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