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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds real behavioral value beyond that: it lists the returned content (reviewer, date, sentiment, diner type, ordered menu items) and warns that written reviews may be fewer than the headline rating count, which prevents a miscounting error.

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?

Three tight sentences with zero filler. The core purpose is front-loaded, followed by the sort behavior, then the caveat and alternative routing.

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?

An output schema exists, so the description need not explain return values, yet it still summarizes them. For a read-only review-fetch tool with a fully documented schema, nothing an agent needs to invoke it correctly is missing.

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 100%, so all four parameters (including page, page_size, sort, restaurant_id) are already documented. The description only restates the sort options, adding no syntax or constraint detail beyond what the schema provides, so the baseline of 3 is appropriate.

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+resource ('Fetch one Grubhub restaurant's review records and 1-5-star histogram') and enumerates the included fields. It also distinguishes itself from siblings by naming grubhub_search and grubhub_restaurant_menu as the route for other restaurant data.

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?

Explicitly routes the agent to alternatives ('use grubhub_search or grubhub_restaurant_menu for other restaurant data') and clarifies the mismatch between written reviews and headline rating count. It gives clear context but stops short of an explicit 'use this when you need X' trigger statement.

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