Agent Data Tools

by io.github.Nutshell2000

Sitemap parser, URL extractor: documentation URLs from a bounded XML sitemap

sitemap

Read-only

Read one public XML sitemap or sitemap index as structured URLs and source-reported dates. Supports gzip, substring filtering and pagination. Larger sitemaps are read from the start: the first 512 KiB and at most 1000 entries, with a warning. Does not crawl pages or follow child sitemaps. Invalid XML and execution errors are not charged; a valid empty match is charged. Use to find which pages of a docs site to read before calling /extract. Example: url=https://www.sitemaps.org/sitemap.xml. Price $0.002/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Input Schema

Name	Required	Description
`url`	Yes	Absolute public HTTP(S) XML sitemap URL; child sitemaps are not fetched automatically
`offset`	No	Offset into distinct reported matching locations (0-1000, default 0); use nextOffset to continue
`maxUrls`	No	Reported matching locations examined in one page (1-100, default 25); invalid/nonpublic locations may reduce returned entries
`contains`	No	Optional case-insensitive URL substring, at most 200 characters

Output Schema

Name	Required	Description
`url`	Yes
`kind`	Yes
`text`	Yes
`format`	Yes
`offset`	Yes
`entries`	Yes
`hasMore`	Yes
`contains`	Yes
`finalUrl`	Yes
`warnings`	Yes
`fetchedAt`	Yes
`hashFormat`	Yes
`nextOffset`	Yes
`sourceHash`	Yes
`contentHash`	Yes
`reportedEntries`	Yes
`rejectedLocationsInPage`	Yes
`uniqueReportedLocations`	Yes
`matchingReportedLocations`	Yes	Distinct reported locations matching contains, before public-URL validation of the selected page.
`missingOrInvalidLocations`	Yes
`duplicateReportedLocations`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 18, 2026
RemovedOct 18, 2026
AddedOct 18, 2026
RemovedOct 17, 2026

Changed1 schema field changedOct 16, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "contains": {
+      "maxLength": 200,
+      "type": "string"
+    },
+    "contentHash": {
+      "pattern": "^sha256:[a-f0-9]{64}$",
+      "type": "string"
+    },
+    "duplicateReportedLocations": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "entries": {
+      "items": {
+        "properties": {
+          "lastModified": {
+            "description": "Source-reported value; not a verified modification time.",
+            "maxLength": 80,
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "maxLength": 2048,
+            "type": "string"
+          }
+        },
+        "required": [
+          "url",
+          "lastModified"
+        ],
+        "type": "object"
+      },
+      "maxItems": 100,
+      "type": "array"
+    },
+    "fetchedAt": {
+      "type": "string"
+    },
+    "finalUrl": {
+      "type": "string"
+    },
+    "format": {
+      "const": "text"
+    },
+    "hasMore": {
+      "type": "boolean"
+    },
+    "hashFormat": {
+      "const": "text"
+    },
+    "kind": {
+      "enum": [
+        "urlset",
+        "sitemapindex"
+      ]
+    },
+    "matchingReportedLocations": {
+      "description": "Distinct reported locations matching contains, before public-URL validation of the selected page.",
+      "minimum": 0,
+      "type": "integer"
+    },
+    "missingOrInvalidLocations": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "nextOffset": {
+      "minimum": 0,
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "offset": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "rejectedLocationsInPage": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "reportedEntries": {
+      "maximum": 1000,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "sourceHash": {
+      "pattern": "^sha256:[a-f0-9]{64}$",
+      "type": "string"
+    },
+    "text": {
+      "type": "string"
+    },
+    "uniqueReportedLocations": {
+      "maximum": 1000,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "url": {
+      "type": "string"
+    },
+    "warnings": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "url",
+    "finalUrl",
+    "kind",
+    "entries",
+    "reportedEntries",
+    "uniqueReportedLocations",
+    "missingOrInvalidLocations",
+    "duplicateReportedLocations",
+    "rejectedLocationsInPage",
+    "matchingReportedLocations",
+    "contains",
+    "offset",
+    "nextOffset",
+    "hasMore",
+    "warnings",
+    "text",
+    "format",
+    "hashFormat",
+    "contentHash",
+    "sourceHash",
+    "fetchedAt"
+  ],
+  "type": "object"
+}

AddedOct 15, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already cover safety (readOnlyHint, destructiveHint=false, openWorld), but the description adds substantial context beyond them: the 512 KiB / 1000-entry read cap with a warning, gzip support, the fact that invalid XML and execution errors are not charged while a valid empty match is, and the pricing model. The idempotentHint=false is consistent with the explicit per-call charge note.

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-loaded with the core action and scoping, then limits, charging, and an example URL. Dense but each clause carries information; the pricing/credits sentence is slightly mechanical but relevant to cost-aware agents.

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

Completeness5/5

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

An output schema exists, so return values needn't be explained. Given this, the description covers the remaining gaps an agent needs: read limits, no child-sitemap traversal, charging semantics, and a concrete example URL. Nothing material is missing for correct invocation.

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 coverage is 100%, so the baseline is 3. The description adds meaning the schema lacks: substring filtering is case-insensitive, pagination continues from the start with a hard truncation limit, and the read cap explains why offset/maxUrls behavior matters. It stops short of tying each parameter name to its role, so not a 5.

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 ('Read one public XML sitemap or sitemap index as structured URLs and source-reported dates') and draws a hard boundary against crawling and sibling tools. An agent can distinguish it from contents/extract/robots without opening the schema.

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 names the intended use ('find which pages of a docs site to read before calling /extract') and the exclusions ('Does not crawl pages or follow child sitemaps'). The empty-match-is-charged note further clarifies what counts as a useful call.

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

All Agent Data Tools tools Inspect

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.