search_classesLive KARVE (Jeddah) class schedule with real-time availability. Answers what's on, spots left, trainer, and returns a per-class booking link. Read-only. Dates DD/MM/YYYY (KSA). Search in English.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| query | No | ||
| endDate | No | ||
| trainer | No | ||
| category | No | ||
| startDate | No | ||
| includePast | No | ||
| onlyAvailable | No |
| Name | Required | Description | Default |
|---|---|---|---|
| header | Yes | ||
| classes | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (read-only, open-world, idempotent), the description adds context: 'Live' and 'real-time availability' indicate dynamic data, the date format DD/MM/YYYY (KSA) and 'Search in English' specify input constraints, and the booking link return is an extra behavioral detail. It does not contradict 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?
Two sentences that efficiently convey purpose, output, and key constraints (real-time, read-only, date format, language). Every phrase contributes value with no redundancy or filler.
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?
With 8 optional parameters, an output schema, and multiple sibling tools, the description is incomplete. It lacks any parameter guidance, usage examples, or differentiation from class_detail/next_available/studio_info, leaving significant gaps for an agent to correctly invoke the tool.
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 0% and the description mentions none of the 8 parameters (days, query, startDate, endDate, trainer, category, includePast, onlyAvailable). The only reference to 'trainer' is as a returned field, not a filter, so the description provides no guidance on how to construct search parameters.
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 function: searching KARVE (Jeddah) class schedules with real-time availability, spots left, trainer, and per-class booking links. This distinguishes it from siblings like class_detail and next_available by emphasizing broad search and booking link output.
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 implies use for browsing live class schedules and availability but does not explicitly mention when to use it over alternatives like class_detail or next_available. There are no exclusions or alternative tools named, leaving usage context only implicit.
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 role: class_detail for specific class info, next_available for soonest openings, search_classes for full schedule, and studio_info for general facts. Slight overlap between next_available and search_classes is mitigated by distinct purposes: one finds the soonest open class, the other lists the schedule.
All names use snake_case and are readable, but the pattern is mixed: class_detail and studio_info are noun-based, next_available is adjective-based, and search_classes is verb-based. There is no consistent verb_noun pattern across the set.
Four tools is well-scoped for a read-only booking information server, covering schedule, availability, class details, and studio info without redundancy. It is within the typical 3-15 range and each tool earns its place.
The set covers core browsing needs: schedule lookup, finding available classes, getting full class details, and studio policies. It lacks actual booking or cancellation actions, but the descriptions indicate it is designed to provide information and booking links rather than handle transactions, so this is an acceptable scope.