Skip to main content
Glama

Get crisis help: the real emergency number and crisis line for a country

get_crisis_help
Read-onlyIdempotent

PURPOSE: Give the real emergency number and crisis hotlines (suicide or crisis line, text line, domestic violence, child help) for one country, from the verified dataset The Living Bread ships for 53 countries, with its source and the date it was checked. WHEN TO USE: FIRST, before any other tool, whenever a person speaks of harming themselves or someone else, or is in danger ("I want to die", "my friend is suicidal", "he hits me"). WHEN NOT: for loneliness or a wish to talk with no danger, use find_people_to_pray_with (mode a_person_now); for comfort from the Word afterwards, find_scripture_for. Never give a verse in place of a phone number. PARAMETERS: country is the person's country as a name or ISO 3166-1 alpha-2 code ("Nigeria", "GB", "USA"). If you do not know it, ask; this tool never defaults to one country's number. Omit it only to get the list of countries held. OUTPUT: country {code, name} or null; emergency numbers; crisis_line, text_line, domestic_violence and child_help (each name and number, or null); source, verified_at, confidence; rule (how to use the answer); door (the app's crisis page); countries_held when no country matched. BEHAVIOR: read only; a static dataset, no network call. Matching is strict (ISO code, exact name, known alias, or an unambiguous name start of four letters or more) because a wrong line is worse than none. An unheld country returns country null with the general emergency rule (112, 911, 999) and the countries held, never a guessed number. Access: no sign-in; shared limit of 300 requests a minute per IP.

Input Schema

NameRequiredDescriptionDefault
countryNoThe person's country: name or ISO 3166-1 alpha-2 code ("Nigeria", "GB", "Brazil", "USA"). Omit only to list the countries held.

Output Schema

NameRequiredDescriptionDefault
okNoAlways true on a successful answer (errors come back as isError, never here).
idsNoUp to 25 ids found in this answer, for follow-up calls.
licenseNoLicense URL of the returned data (CC BY 4.0 unless stated).
evidenceNoPresent when Scripture was read: translation, canon, corpus version, attribution, and a SHA-256 per passage.
freshnessNoHow current the answer is: kind (scheduled | recently_observed | verified_live | record), retrieved_at, available_now (true only when activity was verified live).
source_urlNoThe first public web page this answer came from or points to.
visibilityNo"public" for shared data, "yours" for the signed-in believer's own data.
answered_byYesThe implementation that answered (the same tool name the signed-in endpoint lists).
attributionNoCredit line for the data: The Living Bread (living-bread.org).
next_actionsNoUp to 4 links the person can open next.
result_stateNo"empty" when nothing matched (count 0, no results); the text then says so plainly.
content_flagsNo["instruction_like_text_removed"] when retrieved text was withheld.
content_layersNoWhich fields are Scripture and which are human interpretation or reflection.
ignored_paramsNoParameters given that this mode does not use.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent safety, but the description adds substantial context: static dataset with no network call, strict matching rules because a wrong line is worse than none, fallback behavior for unheld countries (null + generic rule, never a guessed number), and a rate limit of 300 req/min per IP with no sign-in required.

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?

Long but tightly organized under PURPOSE / WHEN TO USE / PARAMETERS / OUTPUT / BEHAVIOR with the safety-critical instruction front-loaded. The OUTPUT section partially duplicates the existing output schema, which is the one place it spends more words than needed.

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 high-stakes, single-parameter crisis tool, the definition leaves nothing an agent needs unresolved: routing, matching strictness, fallback behavior, and access limits are all stated, far exceeding the minimum given the rich annotations and output schema.

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

Parameters4/5

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

Schema coverage is 100% and already documents the name/ISO-code format, so the baseline is 3. The description adds real value on top: ask the person if the country is unknown, and the tool never defaults to a single country's number.

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 verb+resource (give the real emergency number and crisis hotlines for one country) and scopes it to a verified 53-country dataset with sources. An agent can instantly tell it apart from siblings like find_scripture_for or find_people_to_pray_with.

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?

Explicit when-to-use ('FIRST, before any other tool, whenever a person speaks of harming themselves'), explicit when-not, and names the alternative tools and modes for those adjacent cases. Also states the hard constraint 'never give a verse in place of a phone number.'

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources