Skip to main content
Glama

Search a department's courses

search_courses
Read-only

Find every course a CMU department offers in a semester, including course number, title, and units. Filter by semester and department to identify courses for schedule planning.

Instructions

Every course a department offers in a semester: course number, title and units. Seat availability is not public at CMU, so there is no open/waitlist filter. For sections and times of one course use get_course_details.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "semester": "<semester>",
      "department": "<department>"
    },
    "name": "search_courses"
  }
}

Input Schema

NameRequiredDescriptionDefault
campusNoOnly sections taught on this campus: "Pittsburgh", "Doha", "Silicon Valley", ... Default "any". CMU lists other campuses' sections inside the same course.any
semesterYesSemester code such as "S27" (Spring 2027), "F26" (Fall 2026), "M26" (Summer 2026). Names like 'Spring 2027' also work. Use list_semesters to see what is published.
departmentYesDepartment code, name or course prefix: "CS", "Computer Science" or "15".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real value by explaining a capability the agent might otherwise expect (seat filtering is unavailable) and by naming the returned fields. It stops short of describing result volume or pagination behavior for a potentially large department listing, which keeps it off a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler, with the scope and the returned fields front-loaded before the sibling routing. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly compensates by enumerating the returned fields, and it covers all three parameters via the schema. What's missing is any indication of result size or whether paging/limits apply when a department is large.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with campus, semester and department all documented in the schema itself, so the baseline is 3. The description's mentions of 'a department' and 'in a semester' restate required parameters rather than adding format or edge-case meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a precise scope statement — every course a department offers in a semester — and names the exact fields returned (course number, title, units). It also explicitly separates this tool from get_course_details, so an agent can pick correctly without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states a when-not condition (no open/waitlist filter exists because seat availability isn't public at CMU) and routes the agent to get_course_details for sections and times of a single course. The prohibition and the alternative are both explicit rather than inferred.

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