Search dishes

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), yet the description still adds real behavior: sort=relevance is a single fast search-index call, while cheapest/biggest_discount drop side items and re-confirm prices against live menus, implying slower/fresher results. It stops short of stating index staleness or coverage trade-offs for relevance sort, or any rate/auth limits.

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, front-loaded with the core action and routing rule, followed by the sort-mode behavior and the alternative tool. No sentence is filler or restates a structured field.

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?

With an output schema present (no need to describe returns), full annotation coverage, and 100% parameter documentation, the description supplies everything else an agent needs: purpose, invocation triggers, sort trade-offs, and the sibling alternative.

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 3, but the description adds genuine meaning to the sort parameter by explaining what each mode does to results (fast index lookup vs side-item filtering plus live price confirmation), which the schema's bare "Order of the results." does not convey.

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 (search) plus resource (dishes by name), scope (near a delivery point), and returned fields (price, discount, restaurant). It also explicitly differentiates from the sibling food_find_cheapest, so an agent can route without opening either schema.

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?

Gives concrete trigger phrases ("find X near me", "discounted X") and names the alternative (food_find_cheapest) with the exact condition that selects it (cheapest X across many restaurant menus). The when-to-use / when-to-use-something-else boundary is fully resolved.

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