search_restaurants

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the description doesn't need to cover safety or idempotency. It adds meaningful behavioral context beyond annotations by describing the output composition: verified Bayesian rating scores with thresholds, Tabelog Award winners, 100 Famous Stores, budget info, and reservation status. This tells the agent what kind of results to expect, which is not in the annotations or schema.

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 two sentences and front-loads the core purpose in the first sentence. The second sentence lists several output characteristics but remains a single efficient sentence. There is no redundant fluff or repeated schema information, making it appropriately concise for the level of detail.

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 tool has 9 parameters, but schema coverage is 100% and an output schema exists, so the description need not explain return values. The description covers the key purpose and enriches it with output expectations. It is missing explicit usage differentiation from siblings, but that is covered under usage_guidelines and does not hinder the agent from calling 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 schema fully documents every parameter. The description does not add parameter-specific semantic detail beyond what the schema provides; the rating-threshold explanation is about output values, not input parameters. Per the rubric, with high schema coverage, the baseline is 3, and the description meets that without exceeding it.

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 states a specific verb ('Search') and a clear resource ('top-rated restaurants, cafes, and gourmet dining spots'), and goes beyond a simple noun to specify what kinds of places are included. It also names the data sources (Tabelog Japan and global providers) and lists distinguishing output features (ratings, awards, budgets), making it easy to understand what this tool does and how it differs from a generic search.

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: it is a search tool, so an agent would use it when the user asks to find restaurants. However, it does not explicitly when to use this tool over siblings like 'search_tabelog' or 'suggest_dining', nor does it state when not to use it. There is no alternative routing or exclusion guidance, so it remains at implied usage.

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