Skip to main content
Glama

Liminal

focus

Pass a URL or long text plus task; returns the answer-bearing passages verbatim. Use instead of opening anything over 8,000 chars. More args: get_capabilities(tool=...).

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>",
      "task": "<task>",
      "context": "<context>"
    },
    "name": "focus"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYes
textYes
contextYesUser's goal in one short sentence; no personal data or secrets.
llm_modelNoYour exact model id for analytics, or "unknown"; never guess.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
      -  "text",
      -  "task",
      -  "context",
      -  "llm_model"
      -]New value: +[
      +  "text",
      +  "task",
      +  "context"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / context / description
      Previous value: -"Describe the user's goal in one short sentence. Omit personal data and secrets."New value: +"User's goal in one short sentence; no personal data or secrets."
    • changedInput schema / properties / llm_model / description
      Previous value: -"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."New value: +"Your exact model id for analytics, or \"unknown\"; never guess."
  3. Changed2 schema fields changed
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "text",
      -  "task",
      -  "context"
      -]New value: +[
      +  "text",
      +  "task",
      +  "context",
      +  "llm_model"
      +]
  4. Changed7 schema fields changed
    • addedInput schema / properties / context
      Added value: +{
      +  "description": "Describe the user's goal in one short sentence. Omit personal data and secrets.",
      +  "type": "string"
      +}
    • removedInput schema / properties / detail
      Removed value: -{
      -  "default": "lean",
      -  "title": "Detail",
      -  "type": "string"
      -}
    • removedInput schema / properties / retention
      Removed value: -{
      -  "default": "task_local",
      -  "title": "Retention",
      -  "type": "string"
      -}
    • removedInput schema / properties / task / title
      Removed value: -"Task"
    • removedInput schema / properties / text / title
      Removed value: -"Text"
    • changedInput schema / required
      Previous value: -[
      -  "text",
      -  "task"
      -]New value: +[
      +  "text",
      +  "task",
      +  "context"
      +]
    • removedInput schema / title
      Removed value: -"focusArguments"
  5. Changed1 schema field changed
    • addedInput schema / properties / detail
      Added value: +{
      +  "default": "lean",
      +  "title": "Detail",
      +  "type": "string"
      +}
  6. First observed

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden. It reveals that output consists of answer-bearing passages returned verbatim and that the tool is intended for content over 8,000 characters. It does not state whether fetching a URL is read-only, what network or auth behavior to expect, or any rate limits, leaving meaningful behavioral gaps.

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

Conciseness5/5

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

The description is three sentences with no wasted wording. The core purpose and the 8,000-character threshold are front-loaded, and the pointer to get_capabilities is compact and optional. Every sentence carries useful information.

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

Completeness3/5

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

For a 4-parameter tool with no annotations and no output schema, the description covers purpose, usage threshold, and return nature. It does not fully address safety, read-only behavior, or all parameter roles, but the schema documents two parameters and the description points to get_capabilities for more. It is adequate but not complete.

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 50%, and the description adds meaningful semantics for the undocumented 'text' parameter by saying it accepts a URL or long text, and frames 'task' as the extraction objective. It points to get_capabilities for more args rather than explaining the remaining parameters, so it partially compensates for the coverage gap. Baseline 3 is appropriate.

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 operation: pass a URL or long text plus a task and get back answer-bearing passages verbatim. That clearly distinguishes it from a general fetch/read tool, though it does not explicitly name any sibling tool. The purpose is concrete and actionable.

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 gives a clear usage rule: use this instead of opening anything over 8,000 characters, which implies the tool is for long content. It does not explicitly state when not to use it or name alternative sibling tools for boundary cases. The threshold condition provides useful guidance without being fully explicit about alternatives.

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.