Homeschool Tools

find_curriculum

Read-onlyDestructive

Use this when a user wants to find or get recommendations for homeschool curriculum, educational programs, or learning materials for their children. Searches a curated database of 350+ expert-reviewed homeschool offerings and returns personalized matches based on the child's grade level, learning style, family values, budget, and special needs. subjects is a hard filter results always satisfy. worldview is too, but it widens: a specific worldview request also returns worldview-neutral offerings, which suit any household. grade_level is a hard filter except that an offering with no grade range recorded appears at every grade. budget_max filters on an offering's lowest price, so a result may cost more at higher levels, and one whose price is unknown may appear at any budget. learning_style, special_needs, parent_time, and format_preference influence ranking. Do not use for lesson planning, scheduling, legal compliance questions, or tutoring.

Input Schema

TableJSON Schema

Name	Required	Description
`subjects`	No	Always pass as an array, e.g. ["math","science"]. Use ["all"] for comprehensive curriculum.
`worldview`	No	Family's religious/philosophical preference. 'any' means no preference.
`budget_max`	No	Maximum annual budget in USD, compared against an offering's lowest price. 0 selects offerings with a free tier; many of those also sell paid levels, and an offering whose price is unknown carries no price range at all — so do not tell a family something is free without checking what the result actually shows.
`grade_level`	Yes	The child's current or target grade level.
`parent_time`	No	Daily parent teaching time. 'minimal' = under 1hr, 'moderate' = 1-3hrs, 'intensive' = 3+hrs.
`special_needs`	No	Always pass as an array, e.g. ["adhd","dyslexia"]. Any learning differences or special needs. Use ["none"] if none.
`learning_style`	No	Always pass as an array, e.g. ["visual","hands_on"]. How the child learns best.
`format_preference`	No	Always pass as an array, e.g. ["online","hybrid"]. Preferred curriculum delivery format.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`matches`	Yes
`match_count`	Yes
`no_match_note`	No
`filters_applied`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 6, 2026

TDQS

A4.2/5.0

Behavior1/5

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

The description richly discloses filter semantics and ranking behavior, but annotations mark destructiveHint=true while the description describes a read-only search that 'returns personalized matches.' This directly contradicts the annotation, requiring a score of 1. Annotation Contradiction.

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?

Around 150 words, front-loads the use case, logically groups filter semantics, and closes with exclusions. Every sentence contributes behavioral or selection value without repeating schema boilerplate.

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?

Covers all eight parameters' behavior, states exclusions, and the output schema exists so return values don't need detailing. The contradictory annotation is a gap, but that is an annotation issue, not a description gap.

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

Parameters5/5

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

Despite 100% schema coverage, the description adds critical semantics: subjects and grade_level are hard filters with the no-grade-range exception, worldview widens to include neutral offerings, budget_max compares against lowest price and accepts unknown-price offerings, and learning_style/special_needs/parent_time/format_preference only influence ranking. This goes well 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?

States a specific task ('find or get recommendations for homeschool curriculum, educational programs, or learning materials'), names the resource ('curated database of 350+ expert-reviewed offerings'), and differentiates from siblings by emphasizing personalized matching rather than generic search, comparison, or detail retrieval.

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?

Opens with an explicit 'Use this when...' condition and closes with a 'Do not use for...' list covering adjacent use cases (lesson planning, scheduling, legal, tutoring). It does not name sibling alternatives, but the when/when-not guidance is explicit and actionable.

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

All Homeschool Tools tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation5/5

Each tool targets a distinct stage in the curriculum-discovery workflow: lookup by name, personalized recommendation, single-offering detail, and side-by-side comparison. The descriptions explicitly warn against using the wrong tool (e.g., search_offerings vs find_curriculum), so an agent can reliably disambiguate.

Naming Consistency5/5

All tool names follow a clear verb_noun pattern: compare_offerings, find_curriculum, get_offering_detail, search_offerings. The naming style is uniform and each verb communicates the action at a glance, even though find and search are near-synonyms.

Tool Count5/5

Four tools is well-scoped for a curriculum database server: each tool covers a distinct user need and none feel redundant or missing. The count is not too thin or too heavy for the server's stated purpose.

Completeness5/5

The tool set covers the full curriculum-selection journey: check if a curriculum is covered, get personalized recommendations, view detailed reviews, and compare options side by side. There are no obvious dead ends or missing operations within the stated domain.

Resources

Need Help?