Search NTNU's course catalog for a given year (server-side free-text search over course names and codes; Norwegian terms often match best, e.g. 'maskinlæring' rather than 'machine learning'). Call this first when you don't know the exact course code. Returns course codes, Norwegian names, campus, and exam dates.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| year | Yes | ||
| query | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes the search as server-side free-text and mentions return fields, which is useful. However, it lacks details about pagination behavior despite the page parameter, and does not address potential errors or rate limits. With no annotations, the description could be more comprehensive.
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 concise sentences that are front-loaded with the primary action. No unnecessary words or repetition.
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 tool's complexity (simple search with 3 parameters, no output schema), the description provides adequate context about what is returned. It could be slightly improved by mentioning pagination and the default page size, but overall it is sufficient.
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?
The description partially explains the 'year' and 'query' parameters but does not mention the 'page' parameter at all. With 0% schema description coverage, the description should cover all parameters to help the agent use the tool correctly.
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?
Clearly states the tool searches NTNU's course catalog for a given year using free-text search over course names and codes. Distinguishes itself from sibling tools by being the initial search entry point for unknown course codes.
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 advises to call this first when the exact course code is unknown. Provides a practical tip about Norwegian terms matching best, which helps the agent choose this tool over alternatives like get_course_info that require a course code.
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 targets a distinct aspect of NTNU course data: scheduling, exams, grades, comparisons, search, etc. Overlaps like get_course_schedule and get_weekly_timetable are clearly differentiated by granularity, with descriptions guiding usage.
All tools follow a verb_noun pattern in snake_case, using simple verbs like 'get', 'search', 'check', and 'compare'. The naming is uniform and predictable across all 12 tools.
12 tools is well-scoped for an informational server covering courses, schedules, exams, grades, study plans, and search. Each tool serves a clear purpose without unnecessary redundancy.
The tool set covers core CRUD-like operations for course data, including search, info retrieval, scheduling, exams, grades, and study plans. Minor gaps exist, such as no dedicated tool for study program details or room information, but overall the surface is comprehensive for the domain.