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

The readOnlyHint annotation already establishes this as a safe read operation. The description adds useful behavioral context about scoring logic and name-based lookup ('a named one'), but does not disclose result ordering or return structure. With annotations covering safety, this is adequate but not rich.

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?

Two sentences with no filler. The first sentence states the core action and scoring criteria; the second gives direct usage guidance. Everything earns its place and is front-loaded.

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?

For a simple read-only similarity lookup, the description plus fully documented schema gives the agent the required id/city fields, limit default, and the nature of the result (scored similar restaurants). No output schema exists, but the description's mention of scoring provides enough expectation-setting.

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 input schema already documents id, city, and limit, including the fact that id can be a name and city is always required. The description does not need to restate these; the baseline of 3 applies.

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 announces the operation: 'Find restaurants similar to a named one' and adds how similarity is scored (shared cuisine, occasion, neighbourhood tags, guide co-occurrence). This is specific enough to distinguish it from sibling tools like search_restaurants or compare_restaurants without needing to open the 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?

'Use for 'like X' or 'alternatives to X' requests' explicitly states when to invoke this tool. It does not name excluded cases or alternative siblings like search_restaurants, but the trigger condition is concrete and actionable.

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