classifier.dev

Find the texts the classifier was unsure about

review_uncertain

Classify up to 1,000 texts and return only the ones whose confidence fell under a threshold (default 0.7), each with its two most likely labels. Use this after a bulk classification to decide which items deserve your own attention: the confident answers can be trusted, these are the ones to read. Returns the index of each item so you can map back to your list.

Input Schema

TableJSON Schema

Name	Required	Description
`below`	No	Return items with confidence under this.
`inputs`	Yes	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.
`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
`below`	No
`total`	Yes
`uncertain`	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"
+}

First observedSep 19, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered, and the description adds no contradiction. It contributes useful interpretation semantics (which results to trust) but says nothing about the default data-retention behavior that the non-readOnly annotation implies, so it only partially extends the structured fields.

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 action and filter, then two sentences of guidance and return-shape; nothing is padded. The middle sentence is slightly verbose but its routing advice 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 a 5-parameter tool with full schema coverage and an output schema, the description covers purpose, workflow placement and the index-mapping return behavior. The only real gap is the silent absence of any note on the data-retention/cost implications of a non-readOnly classification call.

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 100%, so all five parameters (including the default 0.7 threshold and the share_data retention tradeoff) are already documented in the schema. The description restates the threshold default but adds no syntax or format detail beyond it, so baseline 3 applies.

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 action (classify up to 1,000 texts) plus the filtering behavior that defines the tool (return only items under a confidence threshold, each with its top two labels). This implicitly separates it from sibling bulk-classification tools by its uncertainty-only output, though it never names those siblings.

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?

"Use this after a bulk classification to decide which items deserve your own attention" gives clear workflow context and even supplies an interpretive rule ("the confident answers can be trusted, these are the ones to read"). It stops short of explicitly naming classify_texts as the prerequisite call or stating when-not to use it.

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.