recommend_washRecommend a wash formula for a vehicle given how dirty it is and the season. Pure guidance, no booking.
| Name | Required | Description | Default |
|---|---|---|---|
| season | No | ||
| dirtLevel | Yes | ||
| vehicleType | Yes | e.g. citadine, berline, SUV, utilitaire |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses the tool is guidance-only and does not create bookings. However, it does not detail what the recommendation looks like (e.g., text output) or any prerequisites. Adequate for a simple recommendation 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?
Two sentences, front-loaded with the specific action and resource, then a concise constraint. No superfluous words.
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 3 parameters and no output schema, the description is complete enough: it explains the inputs (dirt level, season) and the nature of the output (guidance). Could optionally mention return format, but not necessary.
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 33% (only vehicleType described). Description mentions 'how dirty it is and the season' linking to dirtLevel and season parameters, but does not add new meaning beyond schema enums. VehicleType is only elaborated in schema. Marginal value added.
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?
Describes the tool as recommending a wash formula based on dirt level and season. The verb 'recommend' and resource 'wash formula' are clear. Distinguishes from siblings like 'find_centers' and 'get_booking' by emphasizing it is guidance only, not booking.
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?
States 'Pure guidance, no booking', which clarifies the tool's advisory role versus booking-related siblings. However, does not explicitly state when to use versus alternatives; the exclusion is implicit. Context from sibling tools helps.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clear, distinct purpose: listing centers, retrieving booking, listing services, recommending wash, and searching slots. No overlap in functionality.
All tool names follow a consistent verb_noun snake_case pattern (e.g., find_centers, get_booking, search_available_slots). No deviations.
5 tools is reasonable for a focused car-wash booking domain, though the set is slightly underpopulated for a full CRUD workflow.
Missing essential tools for creating, updating, or canceling bookings. The server allows discovering services and slots but not completing a reservation, which is a significant gap.