college-scorecard-mcp-server

Compare Schools

scorecard_compare_schools

Read-only

Side-by-side comparison of the first five distinct normalized school IDs, accepting up to 1,000 raw IDs. Remaining IDs are unprocessed; request them separately. Ordinal competition ranks share ties; shared OPEID6 outcomes and mixed-period price rows are unranked. Topics: costs, admissions, outcomes, aid. Use scorecard_get_school for full profiles.

Input Schema

Name	Required	Description	Default
`ids`	Yes	2–1,000 raw school IDs; first five distinct normalized IDs compared.
`topic`	Yes	Comparison topic: costs, admissions, outcomes, or aid.

Output Schema

Name	Required	Description
`rows`	No	Comparison rows — one per metric, with per-school values and ranks.
`error`	No	Present when the call failed. Absent on success.
`topic`	No	The comparison topic used.
`notice`	No	Warning if some requested IDs returned no record.
`schools`	No	Schools in the comparison set, in the same order as the ids input.
`summary`	No	Brief interpretive summary highlighting the most notable relative differences.
`missing_ids`	No	Processed IDs without records.
`unprocessed_ids`	No	Distinct normalized IDs beyond the five-school serving cap.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedNov 3, 2026

changedInput schema / properties / ids / description

Previous value: -"Array of 2–5 school unit IDs to compare."New value: +"2–1,000 raw school IDs; first five distinct normalized IDs compared."

changedInput schema / properties / ids / maxItems
```
Previous value: -5New value: +1000
```

addedOutput schema / properties / missing_ids

Added value: +{
+  "description": "Processed IDs without records.",
+  "items": {
+    "type": "number"
+  },
+  "type": "array"
+}

addedOutput schema / properties / rows / items / properties / values / items / properties / basis

Added value: +{
+  "description": "Period of an effective price.",
+  "enum": [
+    "academic_year",
+    "program_year"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / schools / items / properties / metric_scope

Added value: +{
+  "additionalProperties": false,
+  "description": "Earnings, debt and repayment are pooled at OPEID6; completion is campus-specific.",
+  "properties": {
+    "completion": {
+      "const": "campus",
+      "description": "Completion is campus-specific.",
+      "type": "string"
+    },
+    "debt": {
+      "const": "opeid6",
+      "description": "Debt is OPEID6-pooled.",
+      "type": "string"
+    },
+    "earnings": {
+      "const": "opeid6",
+      "description": "Earnings are OPEID6-pooled.",
+      "type": "string"
+    },
+    "repayment": {
+      "const": "opeid6",
+      "description": "Repayment is OPEID6-pooled.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "earnings",
+    "debt",
+    "repayment",
+    "completion"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / schools / items / properties / ope6_id

Added value: +{
+  "description": "Provider OPEID6 identifier, preserving leading zeros.",
+  "type": "string"
+}

addedOutput schema / properties / unprocessed_ids

Added value: +{
+  "description": "Distinct normalized IDs beyond the five-school serving cap.",
+  "items": {
+    "type": "number"
+  },
+  "type": "array"
+}

Changed3 schema fields changedOct 14, 2026

addedOutput schema / properties / rows / items / properties / values / items / properties / availability

Added value: +{
+  "description": "Available number, unavailable with unknown cause, or confirmed privacy suppression.",
+  "enum": [
+    "available",
+    "unavailable",
+    "privacy_suppressed"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / rows / items / properties / values / items / properties / suppressed / description

Previous value: -"True when data is unavailable for this school/metric."New value: +"True only for explicit provider privacy markers."

changedOutput schema / properties / rows / items / properties / values / items / required

Previous value: -[
-  "school_id",
-  "suppressed"
-]New value: +[
+  "school_id",
+  "suppressed",
+  "availability"
+]

First observedOct 13, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the read-only and open-world annotations, it discloses that only the first five distinct normalized IDs are processed and all remaining IDs are left unprocessed. It also explains non-obvious ranking behavior: ordinal competition ranks share ties, while shared OPEID6 outcomes and mixed-period price rows are unranked.

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

Conciseness4/5

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

The description is compact and front-loads the comparison scope and processing limit before covering ranking caveats and the alternative tool. The topic list duplicates the schema enum, and the ranking sentence is dense, but there is little overall waste.

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

Completeness5/5

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

For a comparison tool with several edge cases, it covers processing limits, leftover-ID handling, ranking exceptions, topic scope, and the full-profile alternative. Combined with the complete input schema, output schema, and annotations, this provides sufficient context to select and invoke the tool correctly.

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%, and the schema already documents accepted ID forms, the 2–1,000 range, first-five behavior, and the topic enum. The description reiterates normalization, truncation, and topics but adds little parameter-specific meaning beyond those structured fields, so the high-coverage baseline applies.

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 clearly states a side-by-side school comparison, its five-distinct-ID scope, and the available comparison topics. It also distinguishes the tool from scorecard_get_school, which is intended for full profiles.

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 gives an explicit alternative and selection condition: use scorecard_get_school for full profiles rather than comparison. It also tells the agent to request IDs beyond the first five separately, providing clear guidance for oversized inputs.

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

All college-scorecard-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.