Skip to main content
Glama
Sign In

SoapBox Faith

by io.github.alansafahi
OverviewDiscussionsAdmin

compose_prayer_request

Help a member put something into words and post it to their church's prayer wall. Use this rather than submit_prayer_request whenever you helped them word it. TWO CALLS, ON PURPOSE. Call once without confirmed and NOTHING is posted: you get back will_post, the exact text and visibility, plus problems — things worth raising, like a public request naming someone who has not been asked, or a phone number that would be visible to the whole church. Show the member that exact text. When they agree, call again with the same content and confirmed: true. These are their words, going to their congregation under their name. Do not post a version they have not seen, and do not silently fix anything in problems — raise it with them and let them decide. If you helped with the wording, say so. YOU DO NOT PRAY. Posting asks a human community to pray. Never say or imply that you are praying for them, holding them in prayer, lifting them up, or interceding — it is false, and it quietly substitutes software for their church. This applies to you whatever assistant you are. After posting, check_prayer_status tells them how many PEOPLE are praying, which is the thing actually worth saying. If the request suggests the member may be in danger, the response carries crisis resources and will not post until you confirm they have seen them (crisis_acknowledged: true). This is not a refusal — their request still posts. Show them the resources, then proceed. Never reword what they wrote to get past it.

Input Schema

NameRequiredDescriptionDefault
contentYesThe request in the member's own words. Post what they said, not a polished version they have not approved. At most 500 characters.
confirmedNoStep 2 only. True means the member has seen the exact text in will_post and agreed to post it. Omit on the first call.
is_privateNoTrue keeps it to the member's own account; false posts it to their church's prayer wall where its members can pray for it.
community_idNoPublic requests only: the church whose prayer wall it goes on. Omit it when the member has one church. When they have several, the preview lists them in `choose_from`: ask the member which, then pass it. A member with no church can only post privately.
consent_tokenYesThe member's SoapBox consent token with the 'prayer:write' scope, generated in the SoapBox app.
crisis_acknowledgedNoStep 2 only, and only when the first call returned crisis resources: true means you have shown the member those resources. Their request then posts.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / community_id
      Added value: +{
+  "description": "Public requests only: the church whose prayer wall it goes on. Omit it when the member has one church. When they have several, the preview lists them in `choose_from`: ask the member which, then pass it. A member with no church can only post privately.",
+  "examples": [
+    "b3095717-5cc0-4213-8964-a01a5ee6b250"
+  ],
+  "format": "uuid",
+  "type": "string"
+}
    • changedInput schema / properties / content / description
      Previous value: -"The request in the member's own words. Post what they said, not a polished version they have not approved."New value: +"The request in the member's own words. Post what they said, not a polished version they have not approved. At most 500 characters."
    • changedInput schema / properties / content / maxLength
      Previous value: -2000New value: +500
    • changedInput schema / properties / is_private / description
      Previous value: -"True keeps it to the member's own account; false posts it to the community wall where their church can pray for it."New value: +"True keeps it to the member's own account; false posts it to their church's prayer wall where its members can pray for it."
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only give generic mutation hints; the description adds the critical behavior that the first call posts NOTHING and returns will_post/problems, that consent requires the 'prayer:write' scope, that crisis responses block posting until crisis_acknowledged, and that public requests can expose phone numbers or unnamed people. This is substantial context beyond the structured fields and consistent with destructiveHint=false.

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?

Front-loaded with the two-call contract and heavily structured into short declarative blocks. It is long, and the 'YOU DO NOT PRAY' passage is verbose, but nearly every line carries behavior an agent would otherwise get wrong.

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?

No output schema exists, so the description must explain returns — and it does: will_post, problems, choose_from, and crisis resources. Combined with the consent, privacy, and crisis mechanics, an agent has everything needed to call this correctly in either step.

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 schema already documents each parameter; the description adds sequencing meaning — that `confirmed` and `crisis_acknowledged` are step-2-only flags, and that `community_id` may come from a `choose_from` list in the preview. It stops short of restating formats, which is fine given the rich 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 verb+resource ('put something into words and post it to their church's prayer wall') and explicitly contrasts with the sibling submit_prayer_request ('Use this rather than submit_prayer_request whenever you helped them word it'). An agent can route between the two without opening either 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?

Explicit when/when-not: use this when you helped word the request, use submit_prayer_request otherwise. It also specifies the two-call sequence (preview then confirmed: true), the crisis branch, and the never-reword rule — conditions an agent could not infer.

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

All SoapBox Faith toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources