Skip to main content
Glama

Score texts against your own categories

classify
Read-only

Labels up to 20 texts with 2 to 20 labels you choose, with a confidence from 0 to 1 and a one-line reason per text. One label per text, or several with multi true. Uses the chat model with JSON output; labels are as good as the model's reading of them. Price: $0.002 per successful call, paid with x402 (USDC on Base, Solana and 10 more networks); failed calls are not charged.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "labels": "<labels>"
    },
    "name": "classify"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoOne text (or texts)
multiNotrue when a text may take several labels
textsNoUp to 20 texts
labelsYes2 to 20 different labels

Output Schema

NameRequiredDescriptionDefault
modelNo
sourceNo
resultsNo
checkedAtNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only cover readOnlyHint and openWorldHint; the description adds real operational context: hard caps of 20 texts and 2-20 labels, dependence on the chat model including an honest 'labels are as good as the model's reading' caveat, and full cost disclosure. The pricing clause tells the agent exactly what a call costs ($0.002 per successful call), which networks payment runs over (USDC on Base, Solana, 10 more), and that failed calls are free — material for an agent deciding whether to invoke. It stops short of describing latency, retry or quota behavior.

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?

Three compact sentences with the core capability front-loaded, then modes, then cost — a sensible priority order. The pricing sentence is long but each clause (price, payment rail, failure policy) carries distinct decision-relevant information, so little is wasted.

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 re-explained, yet the description still previews confidence and reason, and it covers cost, payment, limits, and the model-quality caveat. The only real gap for an agent is the ambiguity between the singular 'text' and plural 'texts' inputs, which neither the description nor the schema resolves.

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 the schema already documents all four parameters, giving a baseline of 3. The description restates the constraints ('up to 20 texts', '2 to 20 labels', multi means several labels) but adds no syntax, ordering, or default semantics beyond that — notably it does not clarify how 'text' and 'texts' interact or which wins.

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 ('labels texts with labels you choose') plus the exact output shape (confidence 0-1 and one-line reason per text), and the cardinality bounds (up to 20 texts, 2-20 labels). The mention that it 'uses the chat model with JSON output' implicitly separates it from the generic chat sibling, which returns free-form text.

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

Usage Guidelines3/5

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

It explains the in-tool choice between single-label and multi-label mode ('one label per text, or several with multi true'), which is genuine usage guidance. However, it never says when to prefer this over the chat sibling or over doing classification locally, and gives no exclusions or prerequisites beyond the size caps.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources