Skip to main content
Glama

Saber

by app.saber.mcp
OverviewDiscussionsAdmin

monitors-create

Create a monitor

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
__requestBodyYesRequest body

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / __requestBody / properties / webhook / allOf
      Previous value: -[
-  {
-    "additionalProperties": {},
-    "properties": {
-      "interval": {
-        "enum": [
-          "daily",
-          "weekly"
-        ],
-        "type": "string"
-      },
-      "intervalSignalLimit": {
-        "maximum": 10000,
-        "minimum": 1,
-        "type": "integer"
-      },
-      "url": {
-        "format": "uri",
-        "type": "string"
-      }
-    },
-    "required": [
-      "url"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": {},
-    "properties": {
-      "secret": {
-        "description": "Optional HMAC signing secret for deliveries; never echoed back.",
-        "maxLength": 200,
-        "type": "string",
-        "writeOnly": true
-      }
-    },
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": {},
+    "properties": {
+      "interval": {
+        "enum": [
+          "daily",
+          "weekly"
+        ],
+        "type": "string"
+      },
+      "intervalSignalLimit": {
+        "description": "Maximum signals to deliver per polling interval. Each run delivers at most this many. Over a billing cycle the monitor delivers at most this value times the number of runs its interval allows in the cycle, then waits for the next cycle. When runs overlap, for example a manual trigger during a scheduled run, the cycle total can exceed this by at most one run's limit per overlapping run. For ipo_stage_changed, ipo_rumoured and repo_engaged, which Saber checks every few minutes on its own schedule, the limit bounds each check rather than each interval, and the billing-cycle bound is the effective ceiling.",
+        "maximum": 10000,
+        "minimum": 1,
+        "type": "integer"
+      },
+      "url": {
+        "description": "Delivery endpoint. Omit it to create a monitor with no delivery: signals are still detected, stored and charged, and are read back from GET /v1/monitors/{monitorId}/signals instead of being POSTed. A url-less webhook block is still accepted, and is how a caller sets interval and intervalSignalLimit without configuring delivery.",
+        "format": "uri",
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "additionalProperties": {},
+    "properties": {
+      "secret": {
+        "description": "Optional HMAC signing secret for deliveries; never echoed back.",
+        "maxLength": 200,
+        "type": "string",
+        "writeOnly": true
+      }
+    },
+    "type": "object"
+  }
+]
  2. Changed1 schema field changed
    • changedInput schema / properties / __requestBody / properties / checks / items / properties / type / enum
      Previous value: -[
-  "job_posted",
-  "social_posted",
-  "funding_raised",
-  "investment_made",
-  "ipo_announced",
-  "ipo_stage_changed",
-  "repo_engaged"
-]New value: +[
+  "job_posted",
+  "social_posted",
+  "funding_raised",
+  "investment_made",
+  "ipo_announced",
+  "ipo_stage_changed",
+  "repo_engaged",
+  "ipo_rumoured"
+]
  3. Changed1 schema field changed
    • changedInput schema / properties / __requestBody / properties / checks / items / properties / type / enum
      Previous value: -[
-  "job_posted",
-  "social_posted",
-  "funding_raised",
-  "investment_made",
-  "ipo_announced",
-  "ipo_stage_changed"
-]New value: +[
+  "job_posted",
+  "social_posted",
+  "funding_raised",
+  "investment_made",
+  "ipo_announced",
+  "ipo_stage_changed",
+  "repo_engaged"
+]
  4. Added

TDQS

C2.4/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false and idempotentHint=false, and the description 'Create a monitor' is consistent with a mutation. However, the description adds no behavioral detail beyond the annotations – it does not mention potential billing charges, delivery behavior, or the ability to create a monitor without a webhook. It relies entirely on the schema for such context.

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?

The description is a single concise sentence with no fluff. It is front-loaded with the verb and object, but it is so minimal that it conveys almost no information. It is appropriately sized in that it is not verbose, though it could arguably be longer to be useful.

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

Completeness2/5

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

Given the tool's highly complex schema with nested objects and detailed field descriptions, the one-sentence description is inadequate. It provides no high-level overview of what a monitor is, how to choose between list/market targets, or what happens on creation. The schema does most of the heavy lifting, but the description does not help an agent understand the overall purpose or decision points.

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%, with rich descriptions for fields like webhook.url and intervalSignalLimit. The tool description adds nothing about parameters, so the baseline of 3 applies; the schema carries all parameter semantics.

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

Purpose2/5

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

The description 'Create a monitor' is essentially a tautology – it restates the tool name (monitors-create). It states a verb and resource but does not add any distinguishing context, such as what a monitor is or how it differs from monitors-create_action. It is minimally clear but adds no value beyond the name.

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?

The description gives no guidance on when to use this tool versus alternatives. It does not mention any conditions, prerequisites, or contrast with sibling tools like monitors-create_action or monitors-update. An agent receives no directional help.

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

All Saber toolsInspect
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