Ietf Datatracker

Documents Search

documents_search

Read-onlyIdempotent

Search IETF Datatracker documents with optional filters for state (e.g. "active"), type (draft | rfc | charter), or name substring; returns document names, titles, and statuses.

Input Schema

TableJSON Schema

Name	Required	Description
`type`	No	draft \| rfc \| charter \| conflrev \| …
`limit`	No	1-1000 (default 20).
`offset`	No
`states`	No	Comma-sep state ids (e.g. "active").
`name__contains`	No	Substring filter on the name.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`meta`	No
`objects`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 13, 2026
- addedOutput schema / properties / objects / items / properties / intended_std_level / description
```
Added value: +"(type varies; observed both null and non-null)"
```
- removedOutput schema / properties / objects / items / properties / intended_std_level / type
```
Removed value: -"null"
```
- changedOutput schema / properties / objects / items / properties / pages / type
```
Previous value: -"number"New value: +[
+  "number",
+  "null"
+]
```
- changedOutput schema / properties / objects / items / properties / shepherd / type
```
Previous value: -"null"New value: +[
+  "null",
+  "string"
+]
```

Changed6 schema fields changedSep 22, 2026

removedOutput schema / properties / count

Removed value: -{
-  "description": "Total number of matching documents",
-  "type": "number"
-}

addedOutput schema / properties / meta

Added value: +{
+  "properties": {
+    "limit": {
+      "type": "number"
+    },
+    "next": {
+      "type": "string"
+    },
+    "offset": {
+      "type": "number"
+    },
+    "previous": {
+      "type": "null"
+    },
+    "total_count": {
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

removedOutput schema / properties / next

Removed value: -{
-  "description": "URL to next page of results",
-  "type": [
-    "string",
-    "null"
-  ]
-}

addedOutput schema / properties / objects

Added value: +{
+  "items": {
+    "properties": {
+      "abstract": {
+        "type": "string"
+      },
+      "ad": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "expires": {
+        "type": [
+          "null",
+          "string"
+        ]
+      },
+      "external_url": {
+        "type": "string"
+      },
+      "group": {
+        "type": "string"
+      },
+      "id": {
+        "type": "number"
+      },
+      "intended_std_level": {
+        "type": "null"
+      },
+      "keywords": {
+        "type": "string"
+      },
+      "name": {
+        "type": "string"
+      },
+      "note": {
+        "type": "string"
+      },
+      "notify": {
+        "type": "string"
+      },
+      "pages": {
+        "type": "number"
+      },
+      "resource_uri": {
+        "type": "string"
+      },
+      "rev": {
+        "type": "string"
+      },
+      "rfc": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "rfc_number": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "shepherd": {
+        "type": "null"
+      },
+      "states": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "std_level": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "stream": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "submissions": {
+        "items": {
+          "type": [
+            null,
+            "string"
+          ]
+        },
+        "type": "array"
+      },
+      "tags": {
+        "items": {
+          "type": [
+            null,
+            "string"
+          ]
+        },
+        "type": "array"
+      },
+      "time": {
+        "type": "string"
+      },
+      "title": {
+        "type": "string"
+      },
+      "type": {
+        "type": "string"
+      },
+      "uploaded_filename": {
+        "type": "string"
+      },
+      "words": {
+        "type": [
+          "number",
+          "null"
+        ]
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

removedOutput schema / properties / previous

Removed value: -{
-  "description": "URL to previous page of results",
-  "type": [
-    "string",
-    "null"
-  ]
-}

removedOutput schema / properties / results

Removed value: -{
-  "description": "Array of documents matching the search criteria",
-  "items": {
-    "properties": {
-      "abstract": {
-        "description": "Document abstract",
-        "type": "string"
-      },
-      "name": {
-        "description": "Document name",
-        "type": "string"
-      },
-      "pages": {
-        "description": "Number of pages",
-        "type": [
-          "number",
-          "null"
-        ]
-      },
-      "published": {
-        "description": "Publication date",
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "rfc": {
-        "description": "RFC number if applicable",
-        "type": [
-          "number",
-          "null"
-        ]
-      },
-      "status": {
-        "description": "Document status",
-        "type": "string"
-      },
-      "title": {
-        "description": "Document title",
-        "type": "string"
-      },
-      "type": {
-        "description": "Document type",
-        "type": "string"
-      }
-    },
-    "type": "object"
-  },
-  "type": "array"
-}

Changed2 schema fields changedMay 22, 2026

addedInput schema / examples

Added value: +[
+  {
+    "limit": 50,
+    "type": "rfc"
+  },
+  {
+    "name__contains": "quic",
+    "states": "active",
+    "type": "draft"
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "Paginated documents search results",
+  "properties": {
+    "count": {
+      "description": "Total number of matching documents",
+      "type": "number"
+    },
+    "next": {
+      "description": "URL to next page of results",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "previous": {
+      "description": "URL to previous page of results",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "results": {
+      "description": "Array of documents matching the search criteria",
+      "items": {
+        "properties": {
+          "abstract": {
+            "description": "Document abstract",
+            "type": "string"
+          },
+          "name": {
+            "description": "Document name",
+            "type": "string"
+          },
+          "pages": {
+            "description": "Number of pages",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "published": {
+            "description": "Publication date",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "rfc": {
+            "description": "RFC number if applicable",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "status": {
+            "description": "Document status",
+            "type": "string"
+          },
+          "title": {
+            "description": "Document title",
+            "type": "string"
+          },
+          "type": {
+            "description": "Document type",
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

First observedMay 14, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare the full safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false), so the safety burden is off-loaded. The description restates return contents (names, titles, statuses), which is largely redundant given an output schema exists, and adds no pagination or rate-limit context beyond the schema's limit/offset params.

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?

A single tightly-packed sentence that is front-loaded with the action and resource, then the filters and returns. No filler, though the compound structure packs a lot into one clause.

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?

With an output schema and rich annotations covering safety, the description only needs to convey purpose and filter scope, which it does. It would be complete were it to note when to prefer this over the sibling document/rfc/wgs_search tools.

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 80%, so the schema already documents the parameters well. The description names three of the five filters (states, type, name substring) matching the schema, but adds no syntax or format detail beyond it, and says nothing about limit/offset. Baseline 3 is appropriate.

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?

States a specific verb (Search) plus resource (IETF Datatracker documents) and enumerates the filters and return fields, so the tool's function is unambiguous. It does not, however, differentiate itself from the related sibling tools (document, rfc, search_within, wgs_search), leaving sibling disambiguation to inference.

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

Usage Guidelines2/5

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

The description gives no explicit when-to-use guidance or conditions under which this tool should be preferred over alternatives like document, rfc, or wgs_search. Usage is only implied by the word 'search'; no exclusions or prerequisites are stated.

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

All Ietf Datatracker 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.