Skip to main content
Glama

Muslim Prayer Reminder MCP

Configure User Prayer Preferences

configure_prayer_preferences
Idempotent

Configures prayer calculation parameters, location behavior (fixed or auto_travel), madhab, reminder mode, and notification language in persistent storage.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
localeNoLanguage for reminder text: en or ar
madhabNoJurisprudential Asr shadow calculation: Shafi or Hanafi
userIdYesUnique user identifier
enabledNoWhether prayer reminders are enabled
timezoneNoIANA timezone identifier (e.g. Asia/Riyadh, Europe/London)
fixedCityNoPredefined city name for fixed location (e.g. Riyadh, London)
locationModeNoLocation strategy: auto_travel or fixed
reminderModeNoReminder display policy: prayer_window, exact_window, persistent
fixedCoordinatesNoFixed geographical coordinates
highLatitudeRuleNoHigh latitude twilight adjustment rule
calculationMethodNoIslamic prayer calculation authority
minuteAdjustmentsNoCustom per-prayer minute offsets (-60 to +60)
exactWindowMinutesNoDuration in minutes for exact_window mode

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
successYesWhether configuration succeeded
preferencesYes

Schema Changelog

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

  1. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / fixedCoordinates / additionalProperties
      Removed value: -false
    • removedInput schema / properties / minuteAdjustments / additionalProperties
      Removed value: -false
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare idempotentHint=true, destructiveHint=false, and readOnlyHint=false, so the safety profile is covered. The description adds the useful context that changes are stored in 'persistent storage,' but it does not disclose whether unspecified fields are preserved or reset, or how partial updates behave.

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 a single, dense sentence with the action verb front-loaded and no filler words. It packs the key scopes of configuration into a compact list without sacrificing readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the high schema richness (13 parameters, enums, nested objects) and the existing annotations for idempotency and safety, the description is a sufficient entry point. The only minor gap is the lack of explicit statement about whether calling this tool updates only provided fields or overwrites the entire preference object.

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?

Schema description coverage is 100%, so the input schema fully documents every parameter. The description merely summarizes categories already present in the schema (location, madhab, reminder mode, language) without adding semantic details like defaults, interaction between parameters, or unit context.

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 opens with a specific verb ('Configures') and names the concrete resource: prayer calculation parameters, location behavior, madhab, reminder mode, and notification language. This clearly distinguishes it from the sibling get_* tools, which are all read-only lookups.

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

Usage Guidelines2/5

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

There is no explicit statement of when to use this tool versus the sibling getters, nor any mention of prerequisites or exclusions. The usage is only implied by the verb 'Configures' and the presence of write-oriented annotations, but the description itself gives no direct guidance.

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.

TDQS

A4/5.0
Disambiguation4/5

Most tools have clearly distinct purposes: configuration, preference retrieval, next prayer timing, current-due status, and the full daily timetable. There is slight potential confusion between get_prayer_status and get_next_prayer because both deal with current/upcoming prayer timing, but their descriptions sufficiently separate 'currently due' from 'immediate next.'

Naming Consistency5/5

All tool names follow a consistent get_/configure_ + noun-phrase pattern in snake_case. The naming is predictable and an agent can infer likely behavior from the verb and object.

Tool Count5/5

Five tools is well-scoped for a prayer reminder server. Each tool covers a distinct need without redundancy or bloat.

Completeness4/5

The set covers configuration, preference retrieval, daily schedule, next prayer, and current due status—core reminder workflows are represented. Minor gaps exist such as no ability to retrieve prayer times for arbitrary dates or list calculation authorities, but these are not blocking for the apparent purpose.