Relvato

Change a monitor's settings

update_check_settings

DestructiveIdempotent

Change a monitor's own settings. Each monitor takes only its sections (get_check lists them as editable.sections): checkout (checkout monitors), devices (flow and page monitors), errorScan, brokenLinks, accessibilityPages (accessibility), uptime (the URL, text that must / must not appear, accepted statuses, timeout, alert after N minutes, maintenance windows, an API endpoint's method / body / JSON rules), aiOutput, browseUrl (storefront), shopUrl / productUrl (prices), dkimSelectors (email authentication), structurePages (structure drift), webVitalsDevices (Core Web Vitals). Every address must be a full URL on the site's own domain. A section you pass replaces that section; the rest stays. Turning it on or off and its schedule: update_check. The visual monitor: update_visual_monitor.

Input Schema

TableJSON Schema

Name	Required	Description
`uptime`	No	Uptime: what the probes check and when they alert. The whole section is replaced: fields left out go back to their defaults (except maintenance, kept unless sent)
`checkId`	Yes	The monitor's id
`devices`	No	Flow and page monitors
`shopUrl`	No	Prices: the shop page
`aiOutput`	No	The site's own AI feature: its endpoint (full URL on the site), a fixed prompt, and what the answer must (not) contain
`checkout`	No	Checkout monitors
`browseUrl`	No	Storefront: the shop page (blank = the calibrated one)
`errorScan`	No	Extra pages to scan (full URLs on the site) and error texts to ignore
`productUrl`	No	Prices: a sample product
`brokenLinks`	No	Extra pages to crawl, address fragments to skip, and whether external links are checked too
`dkimSelectors`	No	Email authentication: your mail provider's DKIM selectors (up to 10)
`structurePages`	No	Structure drift: pages to fingerprint
`webVitalsDevices`	No	Core Web Vitals: devices to measure
`accessibilityPages`	No	Accessibility: extra pages to test on top of the key pages (full URLs on the site, up to 20). A new page's issues are reviewed on its first scan, not failed

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 6, 2026

addedInput schema / properties / uptime / properties / body

Added value: +{
+  "description": "POST only: the request body (sent as JSON when it parses as JSON; up to 2,000 characters). No custom headers or secrets",
+  "type": "string"
+}

addedInput schema / properties / uptime / properties / json

Added value: +{
+  "description": "Rules on a JSON answer (up to 10; down when any fails): the value at `path` (\"status\", \"checks.db.ok\", \"items[0].id\") tested with `op` against `value`",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "op": {
+        "enum": [
+          "equals",
+          "not-equals",
+          "contains",
+          "exists",
+          "missing",
+          "lt",
+          "gt"
+        ],
+        "type": "string"
+      },
+      "path": {
+        "description": "Dot path into the JSON answer",
+        "type": "string"
+      },
+      "value": {
+        "description": "What to compare with (a number for lt / gt; not needed for exists / missing)",
+        "type": "string"
+      }
+    },
+    "required": [
+      "path",
+      "op"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / uptime / properties / method

Added value: +{
+  "description": "API endpoints: the request method (default GET)",
+  "enum": [
+    "GET",
+    "HEAD",
+    "POST"
+  ],
+  "type": "string"
+}

Changed2 schema fields changedOct 6, 2026

changedInput schema / properties / uptime / description

Previous value: -"Uptime: what the probes check and when they alert. The whole section is replaced: fields left out go back to their defaults"New value: +"Uptime: what the probes check and when they alert. The whole section is replaced: fields left out go back to their defaults (except maintenance, kept unless sent)"

addedInput schema / properties / uptime / properties / maintenance

Added value: +{
+  "description": "Maintenance windows (up to 10): no uptime alerts and no Uptime run inside them, and an outage that starts inside one counts as downtime only after it ends. Left out = keep the saved windows; [] clears them. A new one-off window can't start in the past",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "days": {
+        "description": "weekly: weekdays, 0 = Sunday … 6 = Saturday",
+        "items": {
+          "type": "number"
+        },
+        "type": "array"
+      },
+      "from": {
+        "description": "once: start, ISO 8601 with a time zone",
+        "type": "string"
+      },
+      "kind": {
+        "enum": [
+          "once",
+          "weekly"
+        ],
+        "type": "string"
+      },
+      "minutes": {
+        "description": "weekly: length in minutes (5-720)",
+        "type": "number"
+      },
+      "note": {
+        "description": "Optional label, e.g. \"Host migration\"",
+        "type": "string"
+      },
+      "start": {
+        "description": "weekly: local start time, HH:MM",
+        "type": "string"
+      },
+      "to": {
+        "description": "once: end, ISO 8601 (at most 7 days after the start)",
+        "type": "string"
+      },
+      "tz": {
+        "description": "weekly: IANA time zone, e.g. Europe/Bucharest",
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Changed1 schema field changedOct 5, 2026

addedInput schema / properties / uptime

Added value: +{
+  "additionalProperties": false,
+  "description": "Uptime: what the probes check and when they alert. The whole section is replaced: fields left out go back to their defaults",
+  "properties": {
+    "absentText": {
+      "description": "Down if the page contains this text",
+      "type": "string"
+    },
+    "alertAfterMin": {
+      "description": "Minutes down before alerting (0-60, default 0 = as soon as both regions confirm)",
+      "type": "number"
+    },
+    "expectText": {
+      "description": "Down if the page doesn't contain this text",
+      "type": "string"
+    },
+    "maxResponseMs": {
+      "description": "The monitor's run warns above this response time (500-30000, default 8000); not counted as down",
+      "type": "number"
+    },
+    "okStatuses": {
+      "description": "Accepted status codes, e.g. \"200-299, 301\" (blank = any non-error answer)",
+      "type": "string"
+    },
+    "timeoutSec": {
+      "description": "Down if there's no answer within this many seconds (5-30, default 15)",
+      "type": "number"
+    },
+    "url": {
+      "description": "Page to check (full URL on the site; blank = the homepage)",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedOct 5, 2026

changedInput schema / properties / checkout / properties / depth / description

Previous value: -"\"ready\" stops at the payment step; \"order\" places a REAL test order (cleaned up by the WordPress plugin)"New value: +"\"ready\" stops at the payment step; \"order\" places a REAL test order (the WordPress plugin marks it, keeps it out of stock, analytics and ad platforms, and removes it)"

Changed1 schema field changedOct 5, 2026

addedInput schema / properties / accessibilityPages

Added value: +{
+  "description": "Accessibility: extra pages to test on top of the key pages (full URLs on the site, up to 20). A new page's issues are reviewed on its first scan, not failed",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

AddedOct 2, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already flag destructive and idempotent, but the description adds important behavioral context: section replacement semantics, the full-URL-on-domain constraint, and which sections apply to which monitor types. This goes beyond the annotations and helps prevent unintended data loss.

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 purpose and constraints, but the dense list of sections and inline parentheticals make it a lengthy single paragraph. Every element is relevant, yet bullet points would improve 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 14 nested parameters, no output schema, and rich annotations, the description is nearly complete: it covers section applicability, URL rules, replacement behavior, and sibling alternatives. It could add a note on prerequisites or error handling, but nothing critical 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 baseline 3. The description adds value by mapping each section parameter to the monitor types that accept it (e.g., checkout for checkout monitors, devices for flow/page monitors) and reiterating the full URL requirement, aiding correct parameter selection.

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 action ('Change a monitor's own settings') and explicitly differentiates from update_check (on/off, schedule) and update_visual_monitor (visual monitors). An agent can distinguish this tool from its siblings immediately.

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?

Tells the agent that each monitor accepts only its sections, references get_check for editable.sections, and names the correct alternatives for toggling/scheduling and visual monitors. It also clarifies replacement semantics (a section passed replaces that section, rest stays).

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

All Relvato 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?