Skip to main content
Glama
OurFamilyWizard MCP

OurFamilyWizard MCP

by chrischall

ofw_sync_messages

Destructive

Sync OurFamilyWizard messages into a local cache to surface new and unread inbox items without marking them read, while resuming bounded history backfills across calls.

Instructions

Sync messages from OurFamilyWizard into the local cache. Returns counts per folder and a list of unread inbox messages whose bodies were NOT fetched (to avoid mark-as-read on OFW). Call ofw_get_message(id) on those to read them. EVERY call re-checks the newest page first, so new messages are picked up promptly even while an old-history backfill is still running; only then does it spend what is left of its budget advancing that backfill. Pass deep:true to walk all OFW pages instead of stopping at the first all-cached page (use to backfill suspected gaps). Sync is BOUNDED and RESUMABLE: on hosted deployments a per-call OFW-request budget (env OFW_SYNC_MAX_REQUESTS, or the maxRequests argument) caps how far one call walks; when the budget is hit the response reports done:false with a note — call again with the SAME arguments to resume. done:false means older history is still being backfilled; it does NOT mean recent messages are missing. Local installs are unbounded by default (done is always true). On a server-configured no-read day (OFW_READ_DAYS / OFW_NO_READ_DAYS) no inbox or sent message body is downloaded at all — new messages are cached from the list (sender, date, subject) and the response carries bodiesWithheld:true; the first sync on a reading day fills in those bodies, except unread inbox ones.

Input Schema

NameRequiredDescriptionDefault
deepNoIf true, walk every OFW page until empty regardless of cache state. Use to backfill gaps. Default false.
foldersNoFolders to sync (default: all three). Must be non-empty if given — an empty list would sync nothing while reporting success.
maxRequestsNoMaximum OFW requests this single call may make before pausing. When hit, the response reports done:false — call again with the same arguments to continue. Omit to use the server default (OFW_SYNC_MAX_REQUESTS, or unbounded on local installs).
confirmTokenNoONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 "confirmation-required" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.
fetchUnreadBodiesNoIf true, also fetch bodies for unread inbox messages — which marks each one READ on OurFamilyWizard and stamps a co-parent-visible "First Viewed" time that cannot be undone. Defaults to the OFW_FETCH_UNREAD_BODIES env var (false unless set). Applies only when the inbox is among the folders synced. Refused outright when OFW_ALLOW_MARK_READ=false or on a no-read day (the response's unreadBodies says which). When the server runs with OFW_CONFIRM_MARK_READ=true, the sync runs WITHOUT marking anything read and then asks the user to confirm opening the listed unread messages (newest 25 per call): a confirmation prompt where the client supports one; otherwise it returns that list plus a confirmToken, and only a repeat call with that token opens them. Show the user the list and wait for their yes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.26.1
    • addedInput schema / properties / confirmToken
      Added value: +{
      +  "description": "ONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 \"confirmation-required\" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.",
      +  "type": "string"
      +}
    • changedInput schema / properties / fetchUnreadBodies / description
      Previous value: -"If true, also fetch bodies for unread inbox messages — which marks each one READ on OurFamilyWizard and stamps a co-parent-visible \"First Viewed\" time that cannot be undone. Defaults to the OFW_FETCH_UNREAD_BODIES env var (false unless set), and is forced off entirely when OFW_ALLOW_MARK_READ=false."New value: +"If true, also fetch bodies for unread inbox messages — which marks each one READ on OurFamilyWizard and stamps a co-parent-visible \"First Viewed\" time that cannot be undone. Defaults to the OFW_FETCH_UNREAD_BODIES env var (false unless set). Applies only when the inbox is among the folders synced. Refused outright when OFW_ALLOW_MARK_READ=false or on a no-read day (the response's unreadBodies says which). When the server runs with OFW_CONFIRM_MARK_READ=true, the sync runs WITHOUT marking anything read and then asks the user to confirm opening the listed unread messages (newest 25 per call): a confirmation prompt where the client supports one; otherwise it returns that list plus a confirmToken, and only a repeat call with that token opens them. Show the user the list and wait for their yes."
  2. Changed1 schema field changedv2.17.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. First observedv2.8.0

TDQS

A4.6/5.0
Behavior4/5

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

With destructiveHint=true already declared, the description still adds substantial non-annotated behavior: per-call request budgets, done:false resumability semantics, no-read-day suppression via bodiesWithheld:true, and the irreversible co-parent-visible 'First Viewed' stamp from fetchUnreadBodies. The only shortfall is that the confirmation/confirmToken flow description is dense and duplicated from the schema rather than clarified.

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 purpose, then constraints and continuation rules, with zero filler sentences. It is long, but the length is justified by a genuinely complex, resumable, side-effecting sync; a couple of clauses (confirmToken mechanics) repeat schema content.

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 resumable, budgeted, potentially destructive sync with no output schema, the description covers what is returned (counts per folder, unread list), continuation semantics, and the read-marking side effect. An agent has everything needed to call it correctly and safely.

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, but the description adds real meaning beyond the schema: it explains the consequence of fetchUnreadBodies (marks read, stamps First Viewed, refused when OFW_ALLOW_MARK_READ=false) and the resume contract for maxRequests. The confirmToken explanation largely restates the schema wording.

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 opening sentence names a specific verb and resource ('Sync messages from OurFamilyWizard into the local cache') and immediately distinguishes the tool from the read path by naming ofw_get_message(id) as the way to read bodies. The agent can tell it apart from ofw_list_messages 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-to-use conditions are given: deep:true for backfilling suspected gaps, call again with the SAME arguments when done:false, and call ofw_get_message to read withheld bodies. It also names the alternative and the exclusion (unread inbox bodies withheld to avoid mark-as-read).

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