Skip to main content
Glama
Sign In

Kilotest

by io.github.jrpool
OverviewDiscussionsAdmin

orderNewTest

Orders testing of a page that has no report yet, with automated approval or rejection and immediate enqueueing if approved. Use this instead of requestNewTest when immediate testing is wanted; testing typically takes 2 to 4 minutes. Returns an order confirmation and disposition details, including, if approved, a report identifier and a question about whether to wait for completion with the awaitTest tool.

Input Schema

NameRequiredDescriptionDefault
URLYes12- to 300-character URL of the page, including the https:// scheme and any query
reasonYes20- to 100-character reason why the page should be tested
descriptionYes1- to 100-character description of the page conforming to the naming convention used in the listPages output

Output Schema

NameRequiredDescriptionDefault
tool nameYes
this requestYes
tool collectionYes
response contentYes
response metadataYes
URLs of similar requests for web usersYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedOutput schema / definitions / ToolsFacts / properties / description / properties / how to generate more findings / properties / approval
      Added value: +{
+  "type": "string"
+}
    • removedOutput schema / definitions / ToolsFacts / properties / description / properties / how to generate more findings / properties / confirmation
      Removed value: -{
-  "type": "string"
-}
    • addedOutput schema / definitions / ToolsFacts / properties / description / properties / how to generate more findings / properties / order confirmation
      Added value: +{
+  "type": "string"
+}
    • addedOutput schema / definitions / ToolsFacts / properties / description / properties / how to generate more findings / properties / request confirmation
      Added value: +{
+  "type": "string"
+}
    • changedOutput schema / definitions / ToolsFacts / properties / description / properties / how to generate more findings / required
      Previous value: -[
-  "new testing",
-  "retesting",
-  "latency",
-  "confirmation"
-]New value: +[
+  "new testing",
+  "retesting",
+  "approval",
+  "latency",
+  "request confirmation",
+  "order confirmation"
+]
  2. Changed2 schema fields changed
    • removedOutput schema / definitions / ReportIdentifier
      Removed value: -{
-  "additionalProperties": false,
-  "properties": {
-    "jobID": {
-      "description": "Job identifier to pass to listIssues once the report is ready.",
-      "type": "string"
-    },
-    "timeStamp": {
-      "description": "Timestamp to pass to listIssues once the report is ready.",
-      "type": "string"
-    }
-  },
-  "required": [
-    "timeStamp",
-    "jobID"
-  ],
-  "type": "object"
-}
    • changedOutput schema / properties / response content / properties / disposition of your order / anyOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "do you want to wait for completion": {
-        "type": "string"
-      },
-      "how you can check for completion": {
-        "type": "string"
-      },
-      "report identifier": {
-        "anyOf": [
-          {
-            "$ref": "#/definitions/ReportIdentifier"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "what happens next": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "what happens next",
-      "report identifier",
-      "how you can check for completion",
-      "do you want to wait for completion"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "do you want to wait for completion": {
+        "type": "string"
+      },
+      "how you can check for completion": {
+        "type": "string"
+      },
+      "report identifier": {
+        "anyOf": [
+          {
+            "description": "Identifier of the report, to pass to listIssues once the report is ready (example: 260503T0432-x9z).",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "what happens next": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "what happens next",
+      "report identifier",
+      "how you can check for completion",
+      "do you want to wait for completion"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
  3. Changed2 schema fields changed
    • changedInput schema / properties / description / description
      Previous value: -"1- to 100-character description of the page conforming to the naming convention used in the listReports output"New value: +"1- to 100-character description of the page conforming to the naming convention used in the listPages output"
    • changedOutput schema / properties / this request / properties / body / properties / description / description
      Previous value: -"1- to 100-character description of the page conforming to the naming convention used in the listReports output"New value: +"1- to 100-character description of the page conforming to the naming convention used in the listPages output"
  4. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true and destructiveHint=false, so the description's job is to add process context — which it does: automated approval/rejection, immediate enqueueing on approval, and a 2-4 minute expected duration. It stops short of saying what a rejected order returns or what happens on duplicate orders, which keeps it from a 5.

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?

Two sentences, front-loaded with the action and its precondition before the sibling comparison. Dense but every clause carries information; the return-shape sentence is slightly long but not redundant.

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 the brief mention of the confirmation and disposition is bonus rather than required. Preconditions, timing, approval behavior, and the awaitTest follow-up are all covered; only edge behavior (rejection outcome, re-ordering the same page given idempotentHint=false) is unaddressed.

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 all three required parameters documented (URL length/scheme, reason length, description naming convention), so the schema carries parameter semantics. The description adds nothing about the parameters beyond what is already in the schema; baseline 3 applies.

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 and resource ('Orders testing of a page') and narrows scope with a precondition ('that has no report yet'), which separates it from orderRetest and getReport. It also names requestNewTest as the contrasting sibling, so an agent can pick between them without reading schemas.

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?

Explicitly says to use this 'instead of requestNewTest when immediate testing is wanted', giving both the alternative and the condition that selects it. It also points to awaitTest for the wait-for-completion follow-up, covering the next step an agent would otherwise have to guess.

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

All Kilotest toolsInspect
Try in Browser
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources