Skip to main content
Glama

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

text_keywords

Read-onlyIdempotent

utilpeek: Extract the keywords and keyphrases of a text. For raw frequencies use text_frequency; for names and places use extract_entities. Returns the top keyphrases of a text by RAKE (phrases between stop words and punctuation, scored by word degree / frequency), with score and count. Typically under 0.3 s. Price: USD 0.002. Free: 10 utilpeek calls per IP per UTC day. The submitted text is never logged or stored. Docs: https://tanod.dev/learn/keyword-extraction-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>"
    },
    "name": "text_keywords"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe text (at most 200,000 characters).
top_nNoKeyphrases to return, best first.
languageNoStop-word language: de, en (default), es, fr, it, nl or pt.en
max_wordsNoLongest keyphrase, in words.

Output Schema

NameRequiredDescriptionDefault
noteNo
errorNoOnly on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
methodNo
sourceNo
keywordsNo
languageNo
candidatesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • removedInput schema / properties / language / title
      Removed value: -"Language"
    • removedInput schema / properties / max_words / title
      Removed value: -"Max Words"
    • removedInput schema / properties / text / title
      Removed value: -"Text"
    • changedInput schema / properties / top_n / description
      Previous value: -"Keyphrases to return, best first (1-100, default 10)."New value: +"Keyphrases to return, best first."
    • removedInput schema / properties / top_n / title
      Removed value: -"Top N"
    • removedInput schema / title
      Removed value: -"text_keywordsArguments"
    • removedOutput schema / properties / keywords / items
      Removed value: -{
      -  "properties": {
      -    "count": {
      -      "type": [
      -        "integer",
      -        "null"
      -      ]
      -    },
      -    "phrase": {
      -      "type": [
      -        "string",
      -        "null"
      -      ]
      -    },
      -    "score": {
      -      "type": [
      -        "number",
      -        "null"
      -      ]
      -    }
      -  },
      -  "type": [
      -    "object",
      -    "null"
      -  ]
      -}
  2. Changed3 schema fields changed
    • addedInput schema / properties / language / description
      Added value: +"Stop-word language: de, en (default), es, fr, it, nl or pt."
    • addedInput schema / properties / top_n / description
      Added value: +"Keyphrases to return, best first (1-100, default 10)."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "candidates": {
      +      "type": [
      +        "integer",
      +        "null"
      +      ]
      +    },
      +    "error": {
      +      "description": "Only on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object."
      +    },
      +    "keywords": {
      +      "items": {
      +        "properties": {
      +          "count": {
      +            "type": [
      +              "integer",
      +              "null"
      +            ]
      +          },
      +          "phrase": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "score": {
      +            "type": [
      +              "number",
      +              "null"
      +            ]
      +          }
      +        },
      +        "type": [
      +          "object",
      +          "null"
      +        ]
      +      },
      +      "type": [
      +        "array",
      +        "null"
      +      ]
      +    },
      +    "language": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "method": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "note": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "source": {
      +      "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 already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, and the description still adds real context beyond them: typical latency under 0.3 s, a per-call price of USD 0.002, a free allowance of 10 calls per IP per UTC day, and the privacy guarantee that submitted text is never logged or stored. It also sketches the shape of the result (top keyphrases with score and count), so the agent knows what comes back.

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 is front-loaded, followed immediately by alternatives, then output shape, then cost and privacy metadata. Every sentence carries operational information, though the pricing, quota, privacy, and docs-link tail makes it denser than strictly necessary for a call decision.

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 single-purpose extraction tool with an output schema, full parameter coverage, and complete annotations, the description covers everything an agent needs: what it does, when to pick it over siblings, expected latency and cost, and how submitted text is handled.

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 four parameters (text, top_n, language, max_words) are already documented in the input schema, and this baseline is appropriate. The description confirms the output ordering ('top keyphrases ... best first') but adds no further detail on top_n or max_words beyond what the schema states.

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 ('Extract the keywords and keyphrases of a text') and names the sibling tools it is not (text_frequency for raw frequencies, extract_entities for names/places). It also names the underlying algorithm, RAKE, so an agent knows the kind of output to expect without opening the schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use-elsewhere routing: raw frequencies go to text_frequency, named entities and places go to extract_entities. There are no exclusions left to inference for the closest competing siblings.

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.