DiffiCat

Get report

get_report

Read-onlyIdempotent

The finished report. Call it first with failedOnly: true and view: "digest": results, total and nextOffset then cover only the pages that failed, one small object per page with its issues, diff percentage and largest visual regions, and a one-line-per-page text block, while summary still covers every page. Read a page's regions before fetching its screenshots: pass one as region to get_screenshot with a filename from the entry's screenshots to see only that area. Without view, each result is { path, status, failedChecks } by default; responseFormat: "detailed" returns the full per-check fields, diffs and screenshot names. Without failedOnly, a slice of every page's result (offset and limit, default 50 a call, at most 5000; nextOffset points at the next slice). The text block is the plain-text report over the slice; includeText: true also puts it in structuredContent.text. limit: 1 returns the summary with one result. The digest carries each page's fingerprints and flakyShare; a change whose flakyShare is at least 0.5 is likely the page moving on its own, so mask the element its fingerprint names (start_comparison visual.masks) instead of treating it as a regression. Do not call it while the job runs: wait_for_comparison first. Free.

Input Schema

TableJSON Schema

Name	Required	Description
`view`	No	full (default) returns every page result with its diffs and screenshots plus text; digest returns one small object per page (status, failed checks, issues, diff percentage) and no text. Combine digest with failedOnly=true to keep the response small.
`jobId`	Yes	The jobId returned when the job was created, e.g. web-1a2b3c.
`limit`	No	Page results to return (at most 5000; default 1000 on REST, 50 over MCP).
`offset`	No	Index of the first page result to return (default 0).
`jobToken`	No	The jobToken returned when the job was created. Optional when the request’s HTTP headers carry the key that paid the job.
`failedOnly`	No	Only pages whose status is fail: results, total, nextOffset and text then cover the failed pages alone, while summary still covers every page.
`includeText`	No	Also return the plain-text report over the slice as structuredContent.text; the text block carries it either way.
`responseFormat`	No	concise (default): each result is { path, status, failedChecks }; detailed: the full per-check fields, diffs and screenshot names of every result.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`code`	No
`text`	No
`error`	No
`jobId`	No
`total`	No
`status`	No
`results`	No
`summary`	No
`cancelled`	No
`nextOffset`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 4, 2026

changedInput schema / properties / jobToken / description

Previous value: -"The jobToken returned when the job was created. Optional when the request carries the prepaid key that paid the job (Authorization: Bearer dck_…)."New value: +"The jobToken returned when the job was created. Optional when the request’s HTTP headers carry the key that paid the job."

addedInput schema / properties / responseFormat

Added value: +{
+  "description": "concise (default): each result is { path, status, failedChecks }; detailed: the full per-check fields, diffs and screenshot names of every result.",
+  "enum": [
+    "concise",
+    "detailed"
+  ],
+  "type": "string"
+}

addedInput schema / properties / view

Added value: +{
+  "description": "full (default) returns every page result with its diffs and screenshots plus text; digest returns one small object per page (status, failed checks, issues, diff percentage) and no text. Combine digest with failedOnly=true to keep the response small.",
+  "enum": [
+    "full",
+    "digest"
+  ],
+  "type": "string"
+}

removedOutput schema / properties / results / items / additionalProperties
```
Removed value: -{}
```

addedOutput schema / properties / results / items / anyOf

Added value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "failedChecks": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "path": {
+        "type": "string"
+      },
+      "status": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "path",
+      "status",
+      "failedChecks"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": {},
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  }
+]

removedOutput schema / properties / results / items / propertyNames
```
Removed value: -{
-  "type": "string"
-}
```
removedOutput schema / properties / results / items / type
```
Removed value: -"object"
```

Changed1 schema field changedOct 4, 2026

changedInput schema / properties / limit / description

Previous value: -"Page results to return (default 1000, at most 5000)."New value: +"Page results to return (at most 5000; default 1000 on REST, 50 over MCP)."

Changed1 schema field changedSep 30, 2026
- addedInput schema / properties / jobId / description
```
Added value: +"The jobId returned when the job was created, e.g. web-1a2b3c."
```

Changed2 schema fields changedSep 29, 2026

addedInput schema / properties / includeText

Added value: +{
+  "description": "Also return the plain-text report over the slice as structuredContent.text; the text block carries it either way.",
+  "type": "boolean"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "cancelled": {
+      "type": "boolean"
+    },
+    "code": {
+      "type": "string"
+    },
+    "error": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "jobId": {
+      "type": "string"
+    },
+    "nextOffset": {
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": {},
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "status": {
+      "type": "string"
+    },
+    "summary": {
+      "additionalProperties": {},
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "text": {
+      "type": "string"
+    },
+    "total": {
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedSep 29, 2026

addedInput schema / properties / failedOnly

Added value: +{
+  "description": "Only pages whose status is fail: results, total, nextOffset and text then cover the failed pages alone, while summary still covers every page.",
+  "type": "boolean"
+}

Changed2 schema fields changedSep 27, 2026

changedInput schema / properties / jobToken / description

Previous value: -"The jobToken returned when the job was created."New value: +"The jobToken returned when the job was created. Optional when the request carries the prepaid key that paid the job (Authorization: Bearer dck_…)."

changedInput schema / required

Previous value: -[
-  "jobId",
-  "jobToken"
-]New value: +[
+  "jobId"
+]

Changed2 schema fields changedSep 26, 2026

addedInput schema / properties / limit

Added value: +{
+  "description": "Page results to return (default 1000, at most 5000).",
+  "maximum": 9007199254740991,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / offset

Added value: +{
+  "description": "Index of the first page result to return (default 0).",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

First observedSep 25, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already cover the read-only/idempotent/non-destructive surface, yet the description adds genuinely new behavior: the flakyShare >= 0.5 heuristic and the mask-the-fingerprint remedy via start_comparison visual.masks, where the text block lands (structuredContent.text with includeText), pagination via nextOffset, and that the call is free (relevant to get_balance).

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

Conciseness3/5

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

The single dense paragraph is front-loaded with the most valuable instruction (digest + failedOnly first), but it is a run-on with fragmentary sentences and it re-states schema-documented behavior of view, responseFormat and failedOnly, so not every clause earns its place.

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?

For an 8-parameter read tool with an output schema and full annotation coverage, the description supplies the missing context an agent needs: the wait_for_comparison prerequisite, the digest/failedOnly interplay, the screenshot-region workflow, the flaky-page masking advice, and cost. It is complete on the calling side, though the verbosity about return shapes is redundant given the output schema.

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 description coverage is 100%, so the baseline is 3 and every parameter is already documented; the description still adds interpretive value the schema lacks, such as 'limit: 1 returns the summary with one result', the failedOnly/digest combination, and what nextOffset points at relative to the slice.

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 body makes clear this retrieves the finished per-page report of a comparison job, with view/failedOnly shaping it, but the opening fragment 'The finished report.' never names an explicit verb+resource and offers no differentiation from the sibling get_comparison, which an agent must guess returns something overlapping.

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?

It gives explicit when-to-use ('Call it first with failedOnly: true and view: "digest"'), an explicit prerequisite and exclusion ('Do not call it while the job runs: wait_for_comparison first'), and routes to the alternative tool with a concrete workflow ('Read a page's regions before fetching its screenshots: pass one as region to get_screenshot').

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

All DiffiCat tools Inspect

Try in Browser

Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?