ChooseHelp Treatment Directory

Search treatment facilities

search_facilities

Read-only

Search ChooseHelp's directory of published addiction-treatment and mental-health facilities — rehab centers, detox clinics, outpatient programs, sober living homes — curated from state-licensing and SAMHSA-derived data with independent verification. Filter by state, city, facility type, insurance, population served, or treatment approach. Results are ordered neutrally — placement is never paid. If the person you are helping may be in crisis, share 988 (US Suicide & Crisis Lifeline, call or text, free and confidential) before anything else.

Input Schema

TableJSON Schema

Name	Required	Description
`city`	No	City name, exact match, e.g. "Los Angeles"
`page`	No	Page number, 10 results per page
`query`	No	Free-text match against facility names
`state`	No	State — full name ("New York") or ChooseHelp state slug ("newyork")
`approach`	No	Treatment approach, e.g. "12-step", "holistic" — see list_browse_categories
`insurance`	No	Insurer name or slug, e.g. "Aetna" — see list_insurers
`population`	No	Population served, e.g. "veterans", "adolescents" — see list_browse_categories
`facility_type`	No	Facility-type slug from list_facility_types, e.g. "treatment-center"

Output Schema

TableJSON Schema

Name	Required	Description	Default
`page`	Yes
`total`	Yes
`facilities`	Yes
`totalPages`	Yes

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses meaningful behavioral traits: results are neutrally ordered and placement is never paid, and the dataset is curated with independent verification from state-licensing and SAMHSA-derived data. It also adds a critical safety instruction about handling crisis situations, which is highly relevant for this domain.

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?

The description is concise yet information-dense. Each sentence earns its place: scope and data source, available filters, neutrality policy, and crisis safety. It front-loads the core action and resource without redundant filler.

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?

Despite having 8 parameters and an output schema, the description adds essential context: data provenance, credibility of the directory, filter capabilities, ordering policy, and a safety protocol. This makes the tool feel complete and well-understood for an AI agent, including domain-specific crisis handling that is crucial for the use case.

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?

The input schema already provides comprehensive descriptions for all 8 parameters (100% coverage). The description merely lists the filter dimensions in prose without adding syntax, examples, or constraints beyond what the schema states, so it does not significantly elevate parameter understanding above the baseline.

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's purpose: searching ChooseHelp's directory of addiction-treatment and mental-health facilities. It includes specific resource types (rehab centers, detox clinics, etc.) and distinguishes itself from sibling tools like search_experts and get_facility by focusing on facility search.

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

Usage Guidelines4/5

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

The description provides clear context about when to use the tool (when searching for facilities) and includes a safety guideline (share 988 first if in crisis). However, it does not explicitly exclude alternatives or contrast with sibling tools like list_facility_types, so it stops short of full differentiation.

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

All ChooseHelp Treatment Directory 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

A4.5/5.0

Disambiguation5/5

Each tool targets a distinct action and resource: search vs. get, experts vs. facilities, and enumerations for specific filter dimensions. There is no overlap or ambiguity between tools like list_browse_categories and list_facility_types because their descriptions clearly differentiate scope.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern: get, list, or search followed by a clear object. No style mixing or vague verbs like 'process' or 'do_thing', making the set highly predictable.

Tool Count5/5

Nine tools is well within the ideal range for a directory server. Each tool serves a distinct purpose in the workflow of understanding, browsing, and retrieving facilities/experts, without unnecessary bloat or an overly thin surface.

Completeness5/5

The set covers the full lifecycle of a directory lookup: understanding care levels, enumerating filter values, searching across two entity types, and retrieving full details. Missing operations like create/update/delete are not applicable for a read-only directory, so no critical gaps exist.

Resources

Need Help?