Skip to main content
Glama

agentkit__extract

Deterministic mid-task tools for AI agents: exact LLM token counting (cl100k), fit a chat message array into a context budget with a trim plan, page to markdown, repair JSON, redact secrets, encode/hash, unit and timezone maths, deadlines and cron. Price: $0.01 per call in USDC on Base (eip155:8453), paid with x402 in params._meta["x402/payment"]. HTTP: POST https://api.firstmention.uk/s/agentkit/extract

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "agentkit__extract"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNo
budgetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • removedInput schema / properties / args
      Removed value: -{
      -  "description": "Arguments for the tool.",
      -  "type": "object"
      -}
    • addedInput schema / properties / budget
      Added value: +{
      +  "type": "number"
      +}
    • addedInput schema / properties / text
      Added value: +{
      +  "type": "string"
      +}
    • removedInput schema / properties / tool
      Removed value: -{
      -  "description": "Tool name, e.g. convert, datetime, extract, validate, repair, redact, deadlines.",
      -  "type": "string"
      -}
    • removedInput schema / required
      Removed value: -[
      -  "tool"
      -]
  2. Changed5 schema fields changed
    • addedInput schema / properties / args
      Added value: +{
      +  "description": "Arguments for the tool.",
      +  "type": "object"
      +}
    • removedInput schema / properties / text
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / properties / tool
      Added value: +{
      +  "description": "Tool name, e.g. convert, datetime, extract, validate, repair, redact, deadlines.",
      +  "type": "string"
      +}
    • removedInput schema / properties / types
      Removed value: -{
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • addedInput schema / required
      Added value: +[
      +  "tool"
      +]
  3. Changed2 schema fields changed
    • addedInput schema / properties / types
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "text"
      -]
  4. Changed3 schema fields changed
    • addedInput schema / properties / text
      Added value: +{
      +  "type": "string"
      +}
    • removedInput schema / properties / url
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / required
      Added value: +[
      +  "text"
      +]
  5. Changed2 schema fields changed
    • removedInput schema / properties / text
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / properties / url
      Added value: +{
      +  "type": "string"
      +}
  6. Changed2 schema fields changed
    • removedInput schema / properties / json
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / properties / text
      Added value: +{
      +  "type": "string"
      +}
  7. Changed3 schema fields changed
    • addedInput schema / properties / json
      Added value: +{
      +  "type": "string"
      +}
    • removedInput schema / properties / text
      Removed value: -{
      -  "type": "string"
      -}
    • removedInput schema / properties / types
      Removed value: -{
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
  8. Changed3 schema fields changed
    • removedInput schema / properties / max_hits
      Removed value: -{
      -  "type": "integer"
      -}
    • removedInput schema / properties / unique
      Removed value: -{
      -  "type": "boolean"
      -}
    • removedInput schema / required
      Removed value: -[
      -  "text"
      -]
  9. Changed8 schema fields changed
    • removedInput schema / properties / from
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / properties / max_hits
      Added value: +{
      +  "type": "integer"
      +}
    • addedInput schema / properties / text
      Added value: +{
      +  "type": "string"
      +}
    • removedInput schema / properties / to
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / properties / types
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / unique
      Added value: +{
      +  "type": "boolean"
      +}
    • removedInput schema / properties / value
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / required
      Added value: +[
      +  "text"
      +]
  10. Changed5 schema fields changed
    • removedInput schema / properties / chain
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / properties / from
      Added value: +{
      +  "type": "string"
      +}
    • removedInput schema / properties / op
      Removed value: -{
      -  "type": "string"
      -}
    • addedInput schema / properties / to
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / value
      Added value: +{
      +  "type": "string"
      +}
  11. Changed8 schema fields changed
    • addedInput schema / properties / chain
      Added value: +{
      +  "type": "string"
      +}
    • removedInput schema / properties / from
      Removed value: -{
      -  "description": "Source unit, e.g. km, kg, F, GB, USD, Km",
      -  "type": "string"
      -}
    • addedInput schema / properties / op
      Added value: +{
      +  "type": "string"
      +}
    • removedInput schema / properties / round
      Removed value: -{
      -  "description": "Decimal places (default 6)",
      -  "type": "integer"
      -}
    • removedInput schema / properties / to
      Removed value: -{
      -  "description": "Target unit; omit to get all equivalents in the same family",
      -  "type": "string"
      -}
    • removedInput schema / properties / value
      Removed value: -{
      -  "description": "Amount to convert",
      -  "type": "number"
      -}
    • removedInput schema / properties / values
      Removed value: -{
      -  "description": "Optional list of values instead of a single value",
      -  "items": {
      -    "type": "number"
      -  },
      -  "type": "array"
      -}
    • removedInput schema / required
      Removed value: -[
      -  "value",
      -  "from"
      -]
  12. First observed

TDQS

D1.8/5.0
Behavior2/5

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

With no annotations supplied, the description carries the full behavioral burden, and it omits what the tool does and returns. It does add genuinely useful non-obvious context that structured fields cannot convey: a fixed price of $0.01 per call in USDC on Base with an x402 payment carried in params._meta, plus an HTTP endpoint — a real prerequisite for invocation. That payment prerequisite is the one substantive disclosure; the operation's semantics and result shape remain entirely undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The single dense paragraph is front-loaded with a suite description rather than this tool's purpose, so the reader reaches the endpoint and price before learning (never learning) what extract does. Nothing about the extract operation itself is present to earn the space it takes.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with no annotations and no output schema, the definition supplies no purpose, no parameter meaning, and no usage routing. Only pricing and transport are covered, which is inadequate for an agent to call this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters, so the description must compensate and does not. Neither 'text' nor 'budget' is mentioned or explained; the word 'budget' only appears in the context of the context-fit capability, which may wrongly suggest this tool trims messages rather than clarifying the parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description never states what 'extract' itself does. It enumerates a suite of unrelated capabilities (token counting, context budgeting, paging, JSON repair, redaction, encoding, maths, cron) under a family banner, so an agent cannot determine the verb or resource for this specific tool, and cannot distinguish it from siblings like agentkit__fit, agentkit__repair, or agentkit__tokens.

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

Usage Guidelines2/5

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

There is no statement of when to call this tool, when not to, or which sibling to prefer for a given task. The capability list reads as suite-level marketing and, if anything, misleads the agent into thinking this one tool performs all of those operations rather than routing it to the correct sibling.

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