Skip to main content
Glama
lzinga

US Government Open Data MCP

by lzinga
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

naep_scores

Read-onlyIdempotent

Retrieve NAEP test scores (Nation's Report Card) to compare U.S. student achievement by subject, grade, state, and demographic group.

Instructions

Get NAEP test scores (Nation's Report Card) — the gold standard for measuring U.S. student achievement. Returns average scale scores by subject, grade, state, and demographic group.

Subjects: 'reading', 'math', 'science', 'writing', 'civics', 'history', 'geography', 'economics', 'tel', 'music' Grades: 4, 8, 12 (math: 4,8 only; economics/tel/music: 8 or 12 only) Variables: 'TOTAL' (all students), 'SDRACE' (race), 'GENDER', 'SLUNCH3' (school lunch/poverty), 'PARED' (parent education) Jurisdiction: 'NP' (national public), or state codes ('CA', 'TX', 'NY', 'MS')

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNoAssessment year: '2022', '2019', '2017'. Default: most recent. Use 'Current' for latest. Append R2 for non-accommodated: '2019R2'.
gradeYesGrade: 4, 8, or 12. Math: 4,8 only. Economics/TEL/Music: grade 8 or 12 only.
subjectYesSubject: 'reading', 'math', 'science', 'writing', 'civics', 'history', 'geography', 'economics', 'tel', 'music'. Aliases: 'mathematics', 'ela', 'us history', 'social studies', 'econ', 'technology'
subscaleNoOverride the default composite subscale. E.g. math: 'MRPS1' (numbers), 'MRPS3' (geometry). See reference for all codes.
variableNo'TOTAL' (default), 'SDRACE' (race), 'GENDER', 'SLUNCH3' (poverty), 'PARED' (parent ed), 'IEP' (disability), 'LEP' (English learners). Crosstab: 'SDRACE+GENDER'
stat_typeNoStatistic type: 'MN:MN' (Average scale score (mean)), 'RP:RP' (Row percent), 'ALC:BB' (% Below Basic (cumulative)), 'ALC:AB' (% At or Above Basic (cumulative)), 'ALC:AP' (% At or Above Proficient (cumulative)), 'ALC:AD' (% At Advanced (cumulative)), 'ALD:BA' (% At Basic (discrete)), 'ALD:PR' (% At Proficient (discrete)), ... (15 total)
jurisdictionNo'NP' (national public, default), or state/district codes: 'CA', 'TX', 'XN' (NYC), 'XC' (Chicago). Comma-separate for multiple.
categoryindexNoFilter specific categories. E.g. for SDRACE: '1' (White), '2' (Black), '3' (Hispanic). For crosstab: '1+1,1+2' (White/Male, White/Female)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2026.4.11
    • removedInput schema / additionalProperties
      Removed value: -false
  2. First observedv2026.3.9

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds that it returns average scale scores, but no information about pagination, rate limits, or output structure. It does not contradict annotations but provides minimal additional behavioral detail.

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 a compact paragraph with bullet-like lines for subjects, grades, variables, and jurisdictions. It front-loads the purpose and includes all key info without excessive verbosity. Slightly long but appropriate for the tool's complexity.

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?

For a complex tool with 8 parameters and no output schema, the description covers the main query dimensions (subject, grade, variable, jurisdiction) and mentions subscale and stat_type indirectly via schema. It doesn't explain how to combine parameters for complex queries, but the schema does. Given the complexity, it is quite complete, though it could mention crosstabs and provide examples.

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 covers all 8 parameters with descriptions, so baseline is 3. The tool description provides a summary of valid subjects, grades, variables, and jurisdictions, which is helpful for quick reference but largely redundant. It adds aliases and crosstab examples that are also present in the schema, offering marginal extra value.

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 the tool retrieves NAEP test scores and lists the key dimensions (subject, grade, variable, jurisdiction). It distinguishes itself from specialized siblings like naep_compare_years or naep_achievement_levels by focusing on raw score retrieval. The phrase 'gold standard' adds context.

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

Usage Guidelines3/5

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

No explicit guidance on when to use this tool vs. the many specialized NAEP siblings. The description implies it is the primary tool for raw scores but does not state exclusions or alternatives, leaving an agent to infer the appropriate choice among similar tools.

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

Deploy Server

Other Tools