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

Annotations only cover readOnly/openWorld; the description adds genuinely non-obvious behavior: $0.002 USDC per successful call via x402, failed calls not charged, max 20 results per page, and an upstream US proxy source. That payment/cost model is critical for an agent deciding to invoke a metered tool.

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 action and location scope, then details, then cost. The long enumeration of return fields is dense but informative; a slightly tighter structure would separate input guidance from output 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?

Covers location inputs, filtering, pagination limits, geographic scope, data source, and pricing. With an output schema present, the description need not explain return values, yet nothing an agent needs to decide and call 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 coverage is 100%, so all six parameters are already documented, including the delivery/pickup enum and the lat/lng-vs-zip grouping. The description adds only marginal param value ('up to 20 per page'); the rest of its detail describes return fields covered by the output schema.

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+scope: Grubhub restaurants delivering to a US ZIP or lat/lng, with optional search text. It also enumerates the returned fields, so an agent knows exactly what it gets versus a generic ecommerce sibling like ecommerce_rappi (LatAm) or product-search tools.

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?

The description clarifies the two location modes (zip OR lat/lng), the delivery/pickup choice, and that the query is optional with concrete examples ('pizza', 'sushi'). US-only scope is stated, which implicitly excludes other markets, but no sibling alternative is named explicitly.

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