classifier.dev

Tag texts with every label that applies

classify_multi_label

Like classify_texts, but each text gets every label that applies (possibly none), with an independent 0-1 score per label. Use this for tagging — topics of an article, components touched by a ticket — where one answer is not enough. Set max_labels to cap how many come back per text. Labels scoring >= 0.7 are kept.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	No	Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries.
`model`	No
`inputs`	No	1 to 1,000 texts to classify. Results come back in the same order.
`labels`	Yes	2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.
`include`	No	With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.
`max_labels`	No	At most this many labels per text, most likely first.
`processing`	No	Optional. Implies Laya if model is omitted; has no effect with explicit Jev. Omit to select fast for up to four labels on one text, or bulk for larger work automatically.
`share_data`	No	Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.
`instructions`	No	Optional extra criteria, e.g. "judge only the service, ignore the food".

Output Schema

TableJSON Schema

Name	Required	Description	Default
`usage`	No
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 4, 2026

changedInput schema / properties / share_data / default
```
Previous value: -falseNew value: +true
```

changedInput schema / properties / share_data / description

Previous value: -"Opt in to retaining this request's text, labels, instructions and model results for model training and operator review in private Cloudflare storage. Doubles per-minute and daily classification quotas. Off by default. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply."New value: +"Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply."

Changed1 schema field changedOct 4, 2026

addedInput schema / properties / share_data

Added value: +{
+  "default": false,
+  "description": "Opt in to retaining this request's text, labels, instructions and model results for model training and operator review in private Cloudflare storage. Doubles per-minute and daily classification quotas. Off by default. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.",
+  "type": "boolean"
+}

Changed4 schema fields changedSep 24, 2026

addedInput schema / oneOf

Added value: +[
+  {
+    "not": {
+      "required": [
+        "url"
+      ]
+    },
+    "required": [
+      "inputs"
+    ]
+  },
+  {
+    "not": {
+      "required": [
+        "inputs"
+      ]
+    },
+    "required": [
+      "url"
+    ]
+  }
+]

addedInput schema / properties / include

Added value: +{
+  "description": "With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.",
+  "items": {
+    "enum": [
+      "markdown",
+      "html"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / url

Added value: +{
+  "description": "Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries.",
+  "maxLength": 8192,
+  "pattern": "^https?://",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "inputs",
-  "labels"
-]New value: +[
+  "labels"
+]

Changed1 schema field changedSep 23, 2026

changedInput schema / properties / model / enum

Previous value: -[
-  "jev",
-  "laya",
-  "kev"
-]New value: +[
+  "jev",
+  "laya",
+  "kev",
+  "chunklaya"
+]

Changed1 schema field changedSep 21, 2026

changedInput schema / properties / model / enum

Previous value: -[
-  "jev",
-  "laya"
-]New value: +[
+  "jev",
+  "laya",
+  "kev"
+]

Changed1 schema field changedSep 20, 2026

changedInput schema / properties / processing / description

Previous value: -"Laya fast accepts up to four labels on one text; bulk handles more."New value: +"Optional. Implies Laya if model is omitted; has no effect with explicit Jev. Omit to select fast for up to four labels on one text, or bulk for larger work automatically."

Changed2 schema fields changedSep 20, 2026

addedInput schema / properties / model

Added value: +{
+  "enum": [
+    "jev",
+    "laya"
+  ],
+  "type": "string"
+}

addedInput schema / properties / processing

Added value: +{
+  "description": "Laya fast accepts up to four labels on one text; bulk handles more.",
+  "enum": [
+    "fast",
+    "bulk"
+  ],
+  "type": "string"
+}

Changed1 schema field changedSep 19, 2026

changedOutput schema / properties / results / items / properties / scores / description

Previous value: -"Independent probability per label."New value: +"Independent model preference per supplied label. Does not validate the input or guarantee correctness."

First observedSep 19, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds real behavioral detail beyond them: a 0.7 score cutoff, the possibility of zero labels, and max_labels capping the returned set. It doesn't discuss cost, quotas, or the share_data retention default, but those live in the schema.

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?

Four tight sentences with the contrast against classify_texts front-loaded and the threshold rule last. No filler, though the opening 'Like classify_texts, but' requires the reader to know the sibling.

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 values need not be explained, and annotations carry the safety profile. For a 9-parameter tool with 89% coverage, the description supplies the scoring/threshold semantics that matter most, leaving only cost and quota behavior to the 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 coverage is 89%, so the baseline is 3, but the description adds meaning the schema lacks: the >= 0.7 keep threshold and the independent-scoring model that governs how labels are returned. max_labels is described as a cap on returned labels, which slightly reframes the schema's 'most likely first' wording.

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?

Opens with a direct contrast against the sibling classify_texts and states the distinguishing behavior: every applicable label per text, each with an independent 0-1 score. An agent can tell this apart from classify_texts and classify_dimensions without opening a schema.

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

Usage Guidelines4/5

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

Gives concrete when-to-use scenarios (topics of an article, components touched by a ticket) and the selecting condition ('where one answer is not enough'), with classify_texts named as the alternative. It stops short of explicitly stating when to prefer classify_texts instead, so the routing is implied rather than spelled out.

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

All classifier.dev tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.