AgentPixel

Check and save installation

check_install

Fetch the pixel's homepage and store whether the tag is there.

    install_status becomes installed or not_installed. check_error says
    why a check could not decide. Evaluator accounts fetch only the fixed
    https://staging.allsourcedata.io/evaluation-test/ page and reject redirects.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`pixel_id`	Yes	pixel_id of the pixel whose homepage to check. Example: px_7a1b2c3d4e5f6a7b

Output Schema

TableJSON Schema

Name	Required	Description	Default
`domain`	Yes
`snippet`	No
`pixel_id`	Yes
`data_kind`	Yes
`checked_at`	No
`check_error`	No
`install_status`	Yes
`consent_enabled`	No
`evaluation_mode`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 10, 2026

changedInput schema / properties / pixel_id / description

Previous value: -"Exact pixel_id returned by create_pixel or list_pixels; never an account ID"New value: +"pixel_id of the pixel whose homepage to check. Example: px_7a1b2c3d4e5f6a7b"

Changed6 schema fields changedOct 9, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / pixel_id / description

Added value: +"Exact pixel_id returned by create_pixel or list_pixels; never an account ID"

addedInput schema / properties / pixel_id / maxLength
```
Added value: +80
```
addedInput schema / properties / pixel_id / minLength
```
Added value: +1
```
addedInput schema / properties / pixel_id / pattern
```
Added value: +"^[A-Za-z0-9_-]+$"
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "check_error": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Check Error"
+    },
+    "checked_at": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Checked At"
+    },
+    "consent_enabled": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Consent Enabled"
+    },
+    "data_kind": {
+      "enum": [
+        "synthetic",
+        "resolved"
+      ],
+      "title": "Data Kind",
+      "type": "string"
+    },
+    "domain": {
+      "title": "Domain",
+      "type": "string"
+    },
+    "evaluation_mode": {
+      "title": "Evaluation Mode",
+      "type": "boolean"
+    },
+    "install_status": {
+      "enum": [
+        "not_checked",
+        "installed",
+        "not_installed",
+        "unreachable"
+      ],
+      "title": "Install Status",
+      "type": "string"
+    },
+    "pixel_id": {
+      "title": "Pixel Id",
+      "type": "string"
+    },
+    "snippet": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Snippet"
+    }
+  },
+  "required": [
+    "pixel_id",
+    "domain",
+    "install_status",
+    "evaluation_mode",
+    "data_kind"
+  ],
+  "title": "Pixel",
+  "type": "object"
+}

First observedOct 9, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the write-plus-network nature is partly covered. The description goes further: it discloses that a real homepage fetch occurs, that state is persisted as installed/not_installed, how failures are surfaced via check_error, and the evaluator-account exception where only a fixed staging URL is fetched and redirects are rejected. It does not explain why the operation is non-idempotent, which is the one annotation left unaddressed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences: the action first, then the two possible persisted outcomes, then the edge-case constraint. No filler, and the most important information is front-loaded.

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 not strictly required, yet the description still names install_status and check_error helpfully. Combined with annotations covering the destructive/open-world profile, an agent has enough to call it correctly; only idempotency behavior remains unexplained.

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?

There is a single parameter and schema coverage is 100%, including an example value and a format pattern, so the schema fully carries parameter meaning. The description adds nothing about pixel_id, which is the correct baseline of 3 when the schema does the heavy lifting.

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?

The description states a specific verb and resource chain: fetch the pixel's homepage and persist whether the tracking tag is present. That is far more concrete than the name alone, though it never names or contrasts a sibling such as get_pixel or setup_status, so an agent must infer which of those is the right alternative.

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

Usage Guidelines3/5

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

There is no explicit 'use this when...' statement or named alternative. The one usage-relevant detail given is scoping for evaluator accounts (fixed URL, redirects rejected), which is a conditional hint but not guidance on when to pick this tool over the sibling status/get tools.

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

All AgentPixel 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.