Mark

Sync Connections

sync_connections

Refreshes integration health. Pass connectionId (the provider from list_connections) to check one integration, retryJobId to retry a failed sync job, both, or neither to refresh all. It works per integration: zernio refreshes Social publishing as a whole, not one social account. Drive also starts an ingest when a folder is configured. When a website post's approval failed because another CMS page uses its slug (get_post reviewNote lists each page's CMS id), pass useCmsPageId with retryJobId to make that page the post's own and retry in one step. Only a page that is not live and no other Mark post owns is accepted; anything else is refused with the reason and nothing is written. In live publish mode the page is published; in draft mode it stays a draft. Related: list_connections, list_channels, get_post.

Input Schema

TableJSON Schema

Name	Required	Description
`retryJobId`	No	Failed sync job id to retry.
`connectionId`	No	Provider from list_connections, e.g. google_drive.
`useCmsPageId`	No	With retryJobId, for a website post that failed on a slug collision: the CMS id of the page holding the slug to use for this post before retrying. Replaces that page's content with the post.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`retry`	No
`ingest`	No
`refresh`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 17, 2026

addedInput schema / properties / useCmsPageId

Added value: +{
+  "description": "With retryJobId, for a website post that failed on a slug collision: the CMS id of the page holding the slug to use for this post before retrying. Replaces that page's content with the post.",
+  "pattern": "^[\\w-]{1,128}$",
+  "type": "string"
+}

First observedOct 1, 2026

TDQS

A3.7/5.0

Behavior2/5

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

The description discloses an overwrite: useCmsPageId 'Replaces that page's content with the post,' and in live mode the page is published. That is a destructive update, yet the annotations declare destructiveHint=false (which per spec means 'only additive updates'). This is an annotation contradiction, though confined to an optional mode, so it is not a flat 1.

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-loads the core purpose, then proceeds mode-by-mode. Dense but every sentence carries operational information (per-integration scope, zernio vs Drive behavior, the slug scenario). Slightly long, but not padded.

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?

With an output schema present, no return-value coverage is needed, and the annotations plus description together cover mutating/external/non-idempotent nature and the special-case workflow. Nothing an agent needs to call it correctly is missing.

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, and the description adds real value on top: it explains that passing both or neither has distinct meaning, and it spells out the exact slug-collision workflow and acceptance guardrails for useCmsPageId that the schema only hints at.

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?

Opens with a specific verb+resource ('Refreshes integration health') and explains the retry/refresh modes with dedicated parameters. It references the related sibling tools (list_connections, list_channels, get_post), though it does not sharply separate itself from update_connection_settings or disconnect_connection.

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

Usage Guidelines4/5

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

Explicitly maps each parameter combination to intent: connectionId checks one integration, retryJobId retries a failed job, both or neither refresh all. It even gives the conditional scenario for useCmsPageId. It stops short of naming when to prefer an alternative tool, so it is context-rich but not fully routable.

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

All Mark tools Inspect

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

Need Help?