certdesk

check_expiry

Read-only

Verdict for up to 5 domains at once: status OK | WARN | CRITICAL | UNKNOWN per domain combining the served certificate (verification, days left, null when the server cannot be measured) and domain registration expiry (RDAP), plus Korean alert lines. Use this for inventories, CI gates (fail unless status is OK) and periodic checks.

Input Schema

Name	Required	Description
`domains`	Yes	Domain names
`critDays`	No	Days before expiry that count as CRITICAL "expiring soon" (default 15; must be < warnDays)
`warnDays`	No	Days before expiry that count as WARN (default 30; the default shrinks for short-lived certificates)

Output Schema

Name	Required	Description	Default
`results`	Yes
`checkedAt`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 4, 2026

addedInput schema / properties / critDays

Added value: +{
+  "description": "Days before expiry that count as CRITICAL \"expiring soon\" (default 15; must be < warnDays)",
+  "maximum": 365,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / warnDays

Added value: +{
+  "description": "Days before expiry that count as WARN (default 30; the default shrinks for short-lived certificates)",
+  "maximum": 365,
+  "minimum": 1,
+  "type": "integer"
+}

Changed1 schema field changedOct 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "checkedAt": {
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "properties": {
+          "domain": {
+            "type": "string"
+          },
+          "headline": {
+            "description": "One-line verdict (Korean)",
+            "type": "string"
+          },
+          "reasons": {
+            "items": {
+              "properties": {
+                "code": {
+                  "type": "string"
+                },
+                "message": {
+                  "type": "string"
+                },
+                "messageEn": {
+                  "type": "string"
+                },
+                "severity": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "code",
+                "severity"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "status": {
+            "description": "UNKNOWN = could not be measured (never treat as OK)",
+            "enum": [
+              "OK",
+              "WARN",
+              "CRITICAL",
+              "UNKNOWN"
+            ],
+            "type": "string"
+          }
+        },
+        "required": [
+          "domain",
+          "status",
+          "headline",
+          "reasons"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "results"
+  ],
+  "type": "object"
+}

First observedSep 26, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already cover read-only/open-world/non-destructive, and the description adds genuine context beyond them: certificate fields may be null when the server cannot be measured, registration expiry comes from RDAP, alert lines are Korean, and defaults shrink for short-lived certificates. It omits operational traits such as rate limits, caching, or latency for up to 5 domains.

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 verdict semantics and status vocabulary before the use-case sentence; the two sentences are dense but earn their space. The first sentence is long and stacks several clauses (verification, days left, null case, RDAP, Korean lines), which slightly hurts scannability.

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?

An output schema exists, so return-value detail is covered, and the description still explains what composes each status and how thresholds behave. Missing only environmental details (per-host rate limits, failure/null handling across a batch of 5), which are minor for this tool's complexity.

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%, including the warnDays/critDays defaults and the shrink-for-short-lived-certificates behavior, so the schema already carries parameter meaning. The description adds only the 'up to 5 domains' cap at the whole-tool level and no new syntax or format detail, making the baseline 3 correct.

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 verb/resource pair ('verdict ... per domain') and enumerates the exact outputs (OK | WARN | CRITICAL | UNKNOWN). The batch scope ('up to 5 domains at once') and the combination of served-certificate and RDAP registration expiry are clear enough to separate it from single-purpose siblings like check_certificate or watch_expiry.

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 names intended uses: inventories, CI gates ('fail unless status is OK'), and periodic checks. That is concrete context, but it never states when not to use it — e.g. no routing to check_certificate for deep single-domain detail or watch_expiry for continuous monitoring, which 'periodic checks' potentially overlaps.

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

All certdesk 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?