grubhub_search

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

With no annotations provided, the description carries the full behavioral burden. It discloses the empty-list behavior for unsupported locations, clarifies delivery vs. pickup scope, and enumerates the fields returned for each restaurant. It does not mention pagination or rate limits, but the description is more transparent than most: it documents both return content and an edge case.

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 long, but the middle section functions as an output-schema substitute because the tool has no output schema. The core purpose is front-loaded in the first sentence, followed by the return-field list and finally the empty-list behavior, which are all service. A slightly trimmer list of return fields could be possible, but each sentence earns its place.

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?

Given no output schema and no annotations, the description is sufficiently complete: it explains return data, the meaning of the id for the outer flow, and empty-list behavior. It could add an explicit note on pagination behavior (e.g., needing multiple page calls when results exceed page_size), but the page and page_size parameters are already documented in the schema, and the description gives the agent enough to call the tool 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 description coverage is 100%, so the baseline is feature. The description adds meaning beyond the schema by clarifying that latitude/longitude define the search center and that the order_method semantics translate to 'delivering to (or offering pickup at)' that location, and by explaining which fields the optional keyword searches over. This is a meaningful increment over the raw schema text.

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 uses a specific verb-resource construction ('Search Grubhub restaurants near a location') and clearly delineates it from the other Grubhub endpoints by noting that each returned restaurant carries the id used by 'every other Grubhub endpoint.' This is a search/listing tool, distinct from grubhub_restaurant, grubhub_restaurant_menu, reviews, and availability 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 implies usage when finding delivery or pickup restaurants near a lat/long, and hints that results feed other Grubhub tools via the id. However, it does not explicitly name sibling alternatives or tell an agent when not to use this tool (e.g., 'to fetch a single restaurant's details, use grubhub_restaurant'). Guidance is implied rather than stated.

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