Skip to main content
Glama

create_checkin

Schedule a check-in for a client with optional questions (confirm-gated). scheduledFor: ISO date; a PAST date records a check-in that already happened (created accepted, the client is not notified) — use import_checkin_history to load many with their answers. question.type: TEXT|NUMBER|SCALE|PHOTO|YES_NO|CHOICE; helpText is shown under a question; a NUMBER question with metric (WEIGHT, WAIST...) also saves the answer to the client's progress chart. title names it for the client (e.g. 'Measurements').

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "clientId": "<clientId>",
      "scheduledFor": "<scheduledFor>"
    },
    "name": "create_checkin"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoWhat the client sees it as, e.g. 'Weekly check-in', 'Measurements'
confirmNoMust be true to actually execute. If false/omitted, returns a preview only.
clientIdYes
questionsNo
scheduledForYesISO date/time, e.g. 2026-06-10 or 2026-06-10T09:00:00Z

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / questions / items / properties / helpText
      Added value: +{
      +  "description": "A line shown under the question, e.g. 'Weigh first thing in the morning'",
      +  "maxLength": 300,
      +  "type": "string"
      +}
    • addedInput schema / properties / questions / items / properties / id
      Added value: +{
      +  "description": "Keep the id from a read when editing, so past answers keep matching",
      +  "type": "string"
      +}
    • addedInput schema / properties / questions / items / properties / metric
      Added value: +{
      +  "description": "NUMBER only: also save the answer to the client's progress chart as this metric. Read in the unit written in the label or answer ('Weight (lbs)', 'Waist (in)'), else the client's own unit setting.",
      +  "enum": [
      +    "WEIGHT",
      +    "WAIST",
      +    "HIP",
      +    "CHEST",
      +    "ARM",
      +    "THIGH",
      +    "NECK"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / questions / items / properties / options
      Added value: +{
      +  "description": "CHOICE only: the answers to pick from",
      +  "items": {
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "maxItems": 10,
      +  "minItems": 2,
      +  "type": "array"
      +}
    • changedInput schema / properties / questions / items / properties / type / enum
      Previous value: -[
      -  "TEXT",
      -  "NUMBER",
      -  "SCALE",
      -  "PHOTO"
      -]New value: +[
      +  "TEXT",
      +  "NUMBER",
      +  "SCALE",
      +  "PHOTO",
      +  "YES_NO",
      +  "CHOICE"
      +]
    • addedInput schema / properties / title
      Added value: +{
      +  "description": "What the client sees it as, e.g. 'Weekly check-in', 'Measurements'",
      +  "maxLength": 120,
      +  "type": "string"
      +}
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare a non-destructive, non-open write, so the safety profile is covered. The description adds genuinely useful behavior beyond them: execution is confirm-gated (a preview otherwise) and a past scheduledFor date creates the record without notifying the client. It does not mention notification timing for future dates or what the preview returns, which are the remaining behavioral gaps.

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 action and density kept high via semicolon-delimited clauses, so an agent can skim to the relevant section. A few clauses restate schema content (the TEXT|NUMBER|SCALE|PHOTO|YES_NO|CHOICE list, helpText's placement) and the sentence runs long, but nothing is truly wasted.

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?

For a 5-parameter write tool with a nested questions array, no output schema and a confirm gate, the description covers the scheduling model, past-date behavior, question typing, metric-to-progress-chart linkage and title rendering. Missing pieces are minor: what the preview contains, and whether/when the client is notified for future-dated check-ins.

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?

With 60% schema coverage the schema already documents confirm, title, helpText, metric and the question type enum, so much of the description's parameter prose is redundant. The one real addition is the scheduledFor past-date semantics (accepted but not notifying the client), which the schema does not state at all and which materially changes how the caller sets the value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb and resource ('Schedule a check-in for a client') with the optional-questions scope and the confirm gate stated up front. It distinguishes itself from import_checkin_history, but says nothing about how it differs from the very similarly named schedule_checkin and upsert_checkin_schedule siblings, leaving real ambiguity.

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

Usage Guidelines3/5

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

It gives one explicit alternative with its condition ('use import_checkin_history to load many with their answers') and explains that a past date records an already-completed check-in. However, the most likely confusion — create_checkin vs schedule_checkin vs upsert_checkin_schedule vs add_checkin_log — is never addressed, so the agent must infer when this is the right entry point.

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.