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

Annotations already establish read-only, non-destructive behavior, and the description adds meaningful context: results are pre-scored with grades and caveats, re-calling only 'adds latency, not a better answer', and missing location causes a location_required refusal instead of a guessed city. No contradiction with the annotations.

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 main purpose is front-loaded in the first sentence, and each subsequent sentence carries distinct usage or behavioral guidance. The length is warranted by the number of common misuse patterns the description proactively prevents, with no filler.

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?

Combined with the output schema and annotations, the description covers everything needed for correct invocation: call budget, query and location relationship, error mode, and how to handle low-confidence or caveated results. Nothing essential is left implicit.

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?

The schema already documents all five parameters with full coverage, so the baseline is 3. The description adds value by defining the query as the full ask and clarifying the location requirement and refusal behavior, while leaving limit and coordinate details to 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?

Opens with a precise deliverable: 'Returns a complete, ranked restaurant recommendation for a dining occasion: the final answer, not a search.' This clearly distinguishes the tool from search and lookup siblings, and tells the agent this is the final recommendation rather than a list of candidates.

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 explicit when and how to use it: call once per question with the full ask, include the place in location, and do not re-call with reworded variations. It also explicitly warns against calling lookup_restaurant to double-check results and instructs relaying caveats instead of searching again, which directly handles the likely alternatives.

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