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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the safety profile is covered. The description adds substantial behavioral context: the two-tier result ordering (full-analyzed first, basic appended), the grading semantics (grade null for basic, preliminary_band from review analysis), and the total_in_area formula. It also discloses the 'message explains when quick-read rows are included'. That's meaningful behavior beyond 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 description is a single dense paragraph but every sentence earns its place: it states the purpose, the result ranking, the two-tier coverage model, the meaning of total_in_area, and the messaging behavior. It's front-loaded with the core function and then layers specifics. For a tool with 8 parameters, it's appropriately sized without fluff.

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 complexity (8 params, output schema exists), the description covers the key behavioral nuances: ordering, coverage levels, how grades are assigned, and the total formula. It doesn't explain return fields in detail, but there's an output schema that likely carries that. It could mention pagination or max values, but those are in the schema. The description is complete enough for an agent to call correctly and interpret results.

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 all 8 parameters are already documented with types and descriptions. The tool description adds a bit around limit (when fewer than limit are available), and it mentions 'preliminary_band' which relates to grading but doesn't add new parameter semantics. It also implies the default sort is 'grade', which matches the schema's description. Since the schema carries the load, baseline 3 is appropriate; the description doesn't add extra param-level meaning beyond what's in 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?

Description says 'Search for restaurants near a location' (verb+resource+scope), and then details exactly what results it returns: graded, ranked results with cuisine, price, and analysis. It distinguishes itself from sibling tools: it's the search tool, while find_restaurant and lookup_restaurant are probably direct lookups, explore_area is area-focused, recommend is recommendation. The specific mention of the two-tier coverage level is a clear differentiator.

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?

It says 'when fewer than limit are available, quick-read restaurants are appended' — that's a when/condition for the inclusion of basic rows. It does not explicitly name sibling tools or contrast alternatives, but it gives clear operational guidance on how result sets behave, which helps an agent decide when to use it and how to interpret results. No explicit exclusions or alternates, but the context is clear for a search tool.

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