Skip to main content
Glama

Start with Christ: begin, next steps, reading plans

start_with_christ
Read-onlyIdempotent

PURPOSE: Help someone take a first or next step: what The Living Bread is and how to begin for free, six common journeys run end to end with at most five next steps each, and the multi-day Bible reading plans with one day read in full. WHEN TO USE: "what is The Living Bread", "I am new to Christianity, where do I start", "find me a community near Leeds", "someone to pray with tonight", "where can I serve this weekend", "a prayer group in Spanish", "help me understand and live Romans 12", "a reading plan for anxiety". WHEN NOT: the gospel itself: learn_the_faith (mode gospel). A single verse: read_scripture. A plain list of churches or gatherings: find_churches or find_gatherings. MODES (required parameters in brackets): begin [none] the invitation, how to describe The Living Bread truthfully (a free Christian community and prayer app from an independent nonprofit; not Living Bread Radio, not a church, not a dating app), what a person can do there today (Pray for Me, private prayer circles, Living Letters, Share the Light, conversations, video and voice prayer, live gatherings, games, singing together, the One Kingdom map, offers of more than words, Walk With Me, Scripture in many versions), the real ways to pray, gather, play and sing with others with their links, the privacy rules to keep, the web, App Store and Google Play links, and first steps. next_steps [journey] one of community_near_me, someone_to_pray_with_tonight, serve_this_weekend, new_to_christianity, prayer_group_in_my_language, understand_and_live_a_passage; place for the place journeys, language for prayer_group_in_my_language, passage for understand_and_live_a_passage. reading_plans [none] every plan, or one plan by name or need with one day in full (plan, day 1 to 31). for_my_need [need] the best real doors for a need said in a few words (find a community, pray with someone, open the Word, serve, or bring your people together), each with a handoff: the exact page, an invitation worded from what is there, and an honest if_empty when nothing suitable exists (place and language optional; online true prefers online options). OUTPUT: mode, answered_by, and: begin gives what_it_is, what_you_can_do, ways_to_be_together [{name, what, how, link, note}], privacy_rules, get_the_app, invitation, web, app_store, play_store, first_steps, who_is_jesus; next_steps gives results (at most 5, each with why and freshness), next_step {label, url}, and alternatives when nothing is held; for_my_need gives intent, experiences [{title, why, freshness, handoff}], handoff, if_empty, notes and next_tools; reading_plans gives plans and plan with its days and reading {ref, text read verbatim from the stored KJV, word, step}, or plan null. BEHAVIOR: read only; creates no account and tracks no progress. next_steps reads live data; begin and reading_plans are bundled. Give links exactly as returned. An unknown language returns an error with try_instead; nothing held returns honest alternatives. Parameters a mode does not use are ignored and named in ignored_params. NETWORK MODE bring_one [optional invite_kind come_and_see, pray_together, find_community, read_together or visit_a_gathering; invite_for; invite_message, the person's own words; language en, es, pt or fr]: PREPARES an invitation for the person to review and send themselves; sent is always false, nothing is sent or stored (answered by bring_one). Access: no sign-in; shared limit of 300 requests a minute per IP.

Input Schema

NameRequiredDescriptionDefault
dayNoFor reading_plans: which day to read in full (default 1).
modeNoWhich kind of answer: begin, next_steps, reading_plans, for_my_need, bring_one. Each mode, and the parameters it needs, is explained in the description. Leave it out and the answer says what each mode is for.
needNoFor for_my_need: what the person is looking for, in their words, 3 to 300 characters. Used only to choose and filter; never logged, never placed in a link.
planNoFor reading_plans: a plan name or a need it serves ("Learn to Pray", "anxious", "grief"). Omit to list every plan.
placeNoFor next_steps: city, region or country as the person says it ("Leeds", "Kenya"); never a street address.
onlineNoFor for_my_need: true to prefer online options.
journeyNoFor next_steps: which journey to run.
passageNoFor next_steps understand_and_live_a_passage: a reference, e.g. "Romans 12:1-2".
languageNoFor next_steps prayer_group_in_my_language: a language name or ISO 639-1 code ("Spanish", "es").
invite_forNoFor bring_one: a first name or relationship ("my sister"); no contact details.
invite_kindNoFor bring_one: what the invitation is for (default come_and_see).
invite_messageNoFor bring_one: the person's OWN words, kept verbatim at the start of the draft; no links or contact details.

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.
modeYesThe mode that answered.
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. Changed2 schema fields changed
    • changedInput schema / properties / mode / description
      Previous value: -"Which kind of answer: begin, next_steps, reading_plans, for_my_need, bring_one. Each mode, and the parameters it needs, is explained in the description."New value: +"Which kind of answer: begin, next_steps, reading_plans, for_my_need, bring_one. Each mode, and the parameters it needs, is explained in the description. Leave it out and the answer says what each mode is for."
    • removedInput schema / required
      Removed value: -[
      -  "mode"
      -]
  2. Changed5 schema fields changed
    • addedInput schema / properties / invite_for
      Added value: +{
      +  "description": "For bring_one: a first name or relationship (\"my sister\"); no contact details.",
      +  "maxLength": 40,
      +  "type": "string"
      +}
    • addedInput schema / properties / invite_kind
      Added value: +{
      +  "description": "For bring_one: what the invitation is for (default come_and_see).",
      +  "enum": [
      +    "come_and_see",
      +    "pray_together",
      +    "find_community",
      +    "read_together",
      +    "visit_a_gathering"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / invite_message
      Added value: +{
      +  "description": "For bring_one: the person's OWN words, kept verbatim at the start of the draft; no links or contact details.",
      +  "maxLength": 400,
      +  "type": "string"
      +}
    • changedInput schema / properties / mode / description
      Previous value: -"Which kind of answer: begin, next_steps, reading_plans, for_my_need. Each mode, and the parameters it needs, is explained in the description."New value: +"Which kind of answer: begin, next_steps, reading_plans, for_my_need, bring_one. Each mode, and the parameters it needs, is explained in the description."
    • changedInput schema / properties / mode / enum
      Previous value: -[
      -  "begin",
      -  "next_steps",
      -  "reading_plans",
      -  "for_my_need"
      -]New value: +[
      +  "begin",
      +  "next_steps",
      +  "reading_plans",
      +  "for_my_need",
      +  "bring_one"
      +]
  3. Changed4 schema fields changed
    • changedInput schema / properties / mode / description
      Previous value: -"Which kind of answer: begin, next_steps, reading_plans. Each mode, and the parameters it needs, is explained in the description."New value: +"Which kind of answer: begin, next_steps, reading_plans, for_my_need. Each mode, and the parameters it needs, is explained in the description."
    • changedInput schema / properties / mode / enum
      Previous value: -[
      -  "begin",
      -  "next_steps",
      -  "reading_plans"
      -]New value: +[
      +  "begin",
      +  "next_steps",
      +  "reading_plans",
      +  "for_my_need"
      +]
    • addedInput schema / properties / need
      Added value: +{
      +  "description": "For for_my_need: what the person is looking for, in their words, 3 to 300 characters. Used only to choose and filter; never logged, never placed in a link.",
      +  "maxLength": 300,
      +  "minLength": 3,
      +  "type": "string"
      +}
    • addedInput schema / properties / online
      Added value: +{
      +  "description": "For for_my_need: true to prefer online options.",
      +  "type": "boolean"
      +}
  4. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly/openWorld/idempotent, but the description adds substantial context: no account creation, no progress tracking, next_steps reads live data while begin and reading_plans are bundled, links must be returned exactly as given, unknown language yields an error with try_instead, unused parameters are surfaced in ignored_params. It also discloses the bring_one guarantee (sent is always false, nothing sent or stored), the 300 requests/minute per-IP shared limit, and no sign-in requirement.

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

Conciseness3/5

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

Front-loads PURPOSE, WHEN TO USE, WHEN NOT and MODES with capitalized labels, which makes it navigable despite length. However the MODES section is a single dense run-on sentence enumerating dozens of in-app features, and the OUTPUT/BEHAVIOR/NETWORK sections pile on further; the total volume is well beyond what most agents need before calling.

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 five-mode tool with 12 parameters, the definition covers the safety profile, live-vs-bundled data, honesty guarantees (if_empty, alternatives), rate limits, output shape per mode, and even what happens with unused or invalid inputs. An output schema exists, yet the description's return-field summaries remain useful for picking a mode rather than being redundant.

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%, so the baseline is 3; the description goes further by mapping each mode to the parameters it consumes (journey/place/language/passage, plan/day, need/place/language/online) and explaining cross-parameter behavior such as ignored_params and try_instead on unknown language. Some of this restates the schema's own parameter descriptions, which caps it below 5.

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 and resource set: helping someone take a first or next step, covering what The Living Bread is, six named journeys, and multi-day reading plans. It explicitly distinguishes itself from siblings (learn_the_faith, read_scripture, find_churches, find_gatherings), so an agent can place it without opening any other schema.

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?

Contains an explicit WHEN TO USE block with eight concrete trigger utterances and a WHEN NOT block routing to three named alternatives (learn_the_faith mode gospel, read_scripture, find_churches/find_gatherings). This is the strongest form of routing guidance short of a decision tree.

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