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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint, so safety is known. The description goes beyond by detailing the bookable flag semantics, the hair/beauty categorization, the shop_name_not_found response behavior, address inclusion for area questions, and the instruction to use reply_header and match user language. This adds substantial behavioral context without contradicting 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 longer than typical but every sentence carries actionable information. It front-loads the purpose and follows with usage context, behavioral details, and response handling. The structure is logical, though it could be slightly more concise without losing value.

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 search tool with an output schema, the description covers all critical aspects: matching semantics, fallback behavior, bookability implications, error handling, location filtering, and response formatting. Given its complexity (3 optional params, category logic, internationalization), nothing essential is missing. The output schema presumably defines the result structure, so the description doesn't need to repeat it.

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 coverage is 100%, but the description enriches parameter understanding: it explains query falls back to service/category search, location matches against address and excludes shops without addresses, and service_type accepts broad and specific categories in multiple languages. These nuances are not present in the schema and materially improve correct usage.

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 opens with a specific verb and resource: 'Search Korean beauty and wellness shops by shop name, service type, or location.' It enumerates the types of businesses covered (salon, spa, nail, etc.) and differentiates itself from booking tools by stating it finds shops and indicates bookability. This clearly distinguishes it from siblings like request_booking or search_availability.

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?

Explicitly says 'Use this tool when a user wants to find a beauty salon, hair salon, nail salon, skincare or facial shop, spa, massage shop, or other K-beauty business in Korea, including requests for appointment or booking options.' It also explains the branching: bookable=true leads to booking through this MCP, bookable=false requires request_booking. It even covers the not-found case with shop_name_not_found and instructs to offer alternatives. This is exemplary guidance.

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