Skip to main content
Glama

Embeddings, Rerank & Speech-to-Text (Tanod)

classify_zero_shot

Read-onlyIdempotent

mlpeek: Classify a text into 1-10 of your labels. For named entities use extract_entities. Returns scores of 1-10 caller-supplied labels for an English text with the nli-deberta-v3-xsmall NLI cross-encoder (Apache-2.0): single-label scores sum to 1 (softmax over the labels), multi_label scores each label on its own; sorted best first. Scores are model confidences, not calibrated probabilities. English only. Runs an open model pinned by hash on Tanod's own CPU (no LLM, no third-party API); an unavailable model is a 503 (not charged). Typically 0.1-0.2 s for a short text and 5 labels, up to about 5 s at 10 labels. Price: USD 0.001. Free: 5 mlpeek calls per IP per UTC day. The submitted text is never logged or stored. Docs: https://tanod.dev/learn/named-entity-recognition-zero-shot-classification-api.html

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": {
      "text": "<text>",
      "labels": "<labels>"
    },
    "name": "classify_zero_shot"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesEnglish text, at most 2,000 characters.
labelsYes1-10 unique candidate labels, each at most 100 characters.
multi_labelNoScore each label on its own instead of making them compete.
hypothesis_templateNoMust contain {} exactly once.This example is about {}.

Output Schema

NameRequiredDescriptionDefault
noteNo
errorNoOnly on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
modelNo
usageNo
labelsNo
truncatedNo
multi_labelNo
hypothesis_templateNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • removedInput schema / properties / hypothesis_template / title
      Removed value: -"Hypothesis Template"
    • removedInput schema / properties / labels / title
      Removed value: -"Labels"
    • removedInput schema / properties / multi_label / title
      Removed value: -"Multi Label"
    • removedInput schema / properties / text / title
      Removed value: -"Text"
    • removedInput schema / title
      Removed value: -"classify_zero_shotArguments"
    • removedOutput schema / properties / labels / items
      Removed value: -{
      -  "properties": {
      -    "label": {
      -      "type": [
      -        "string",
      -        "null"
      -      ]
      -    },
      -    "score": {
      -      "type": [
      -        "number",
      -        "null"
      -      ]
      -    }
      -  },
      -  "type": [
      -    "object",
      -    "null"
      -  ]
      -}
    • removedOutput schema / properties / model / properties
      Removed value: -{
      -  "alias": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  },
      -  "id": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  },
      -  "license": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  },
      -  "revision": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  },
      -  "source": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  }
      -}
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "error": {
      +      "description": "Only on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object."
      +    },
      +    "hypothesis_template": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "labels": {
      +      "items": {
      +        "properties": {
      +          "label": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "score": {
      +            "type": [
      +              "number",
      +              "null"
      +            ]
      +          }
      +        },
      +        "type": [
      +          "object",
      +          "null"
      +        ]
      +      },
      +      "type": [
      +        "array",
      +        "null"
      +      ]
      +    },
      +    "model": {
      +      "properties": {
      +        "alias": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "id": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "license": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "revision": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "source": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        }
      +      },
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "multi_label": {
      +      "type": [
      +        "boolean",
      +        "null"
      +      ]
      +    },
      +    "note": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "truncated": {
      +      "type": [
      +        "boolean",
      +        "null"
      +      ]
      +    },
      +    "usage": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    }
      +  },
      +  "type": "object"
      +}
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only cover safety/idempotency, and the description goes well beyond them: named model and license, self-hosted CPU execution with no third-party API, 503 on model unavailability with no charge, latency expectations (0.1-0.2 s typical, ~5 s at 10 labels), pricing and free-tier limits, and the guarantee that text is never logged or stored. It also flags that scores are model confidences rather than calibrated probabilities, which materially affects downstream interpretation.

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?

Purpose and the sibling hand-off are front-loaded, and nearly every clause carries operational information (model, latency, price, privacy). It is a dense single block rather than a structured list, so the cost/limit details are harder to scan than they could be, but there is little outright filler.

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?

For a paid, rate-limited inference endpoint, the description covers what an agent needs: semantics of the score modes, result ordering, language restriction, failure mode, cost and quota, and privacy. An output schema exists, so the absence of a full return-shape walkthrough is appropriate.

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 genuine meaning by explaining that single-label scores are a softmax summing to 1 while multi_label scores each label independently, and that results are sorted best-first. Those are output-shaping semantics the schema's terse parameter blurbs do not convey.

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?

The opening sentence gives a specific verb and resource (classify a text into 1-10 caller-supplied labels) and immediately scopes it against a named sibling: named entities belong to extract_entities. An agent can distinguish this from extraction tools 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?

It explicitly routes entity work to extract_entities and states the English-only constraint plus the label-count range, which are real usage conditions. It stops short of describing when a caller should prefer multi_label versus the default competing-label mode, leaving that inference to the schema default.

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.