search_ubereats

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

With no annotations provided, the description carries full burden and does so excellently. It discloses network fetching at call time, lack of API key, the data cap via max_results, the envelope structure, non-fatal errors, and empty-list behavior for unrecognized cities or no results. This goes beyond just stating the operation.

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 well-structured into two clear sentences/paragraphs. The first sentence delivers the core purpose, followed by essential operational details. Every sentence provides necessary information without redundancy, making it appropriately concise.

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?

The description covers the return envelope, count/scraper/source_urls/errors fields, error handling, empty results, network implications, and the link to get_ubereats_menu. Given the output schema exists, it still explains the envelope structure adequately, leaving no major gaps for the agent to select and invoke the tool.

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 both parameters already described. The description adds extra meaning by explaining that max_results caps the data list and that city is required for the search. It reinforces the purpose of each parameter in the broader workflow, adding value beyond the 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?

The description clearly states the tool's verb and resource: 'Search Uber Eats for restaurants delivering in a given city'. It distinguishes itself by specifying the output envelope and the relationship to get_ubereats_menu, making it unique among siblings.

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 provides clear context that this is a live network search with no API key, and explicitly mentions the store URL is the input for get_ubereats_menu, indicating a complementary workflow. It lacks explicit 'when not to use' or alternative tool comparisons, but the usage context is clear.

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