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

The annotation readOnlyHint=true already signals a safe read operation, lowering the bar. The description adds useful behavioral detail about the scoring criteria (shared tags, price proximity, guide co-occurrence), which helps the agent understand how results are ranked. However, it does not mention return format, pagination, or error cases, which would be helpful but are not critical for a read-only tool.

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, front-loaded with the core purpose and scoring method. Every word earns its place, and the usage guidance is embedded without extra fluff. It is highly concise and well-structured.

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?

Given the absence of an output schema, the description should hint at the return format. It implies a scored list but does not explicitly state what the agent will receive (e.g., restaurant IDs, full objects, scores). The input parameters are covered by the schema, so the main gap is the output. For a tool with moderate complexity, this is an acceptable but not complete description.

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 each parameter is already documented in the input schema. The description adds context about scoring but does not elaborate on how parameters map to behavior beyond what the schema states. Since the schema handles parameter semantics fully, a baseline of 3 is appropriate.

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 purpose: find restaurants similar to a named one, with specific scoring criteria (cuisine, occasion, neighbourhood, price-tier, guide co-occurrence). It distinguishes itself from siblings like search_restaurants by emphasizing similarity to a specific restaurant rather than general search. The verb 'find' and resource 'restaurants similar' are unambiguous.

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 explicitly says 'Use for \'like X\' or \'alternatives to X\' requests,' giving a clear when-to-use signal. However, it does not mention when not to use it or name alternative tools (e.g., search_restaurants for broader queries), so it lacks explicit exclusions. Still, the usage context is clear and actionable.

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