Skip to main content
Glama

local_summarize

Read-only

Summarize large files or text using a local model without spending Claude's context; open file paths server-side so only the summary returns.

Instructions

PREFER this tool over reading the file with Read when the file is large (>200 lines / >10 KB) and you only need a summary, not the literal content.

Summarizes text or the content of a file with a local model, without spending Claude's context.

Use it to summarize large files/documents: pass 'path' and the file is read server-side, so
the full content does NOT enter Claude's context (only the short summary comes back).
Alternatively pass 'text'. Routes automatically to the mechanical model (short inputs) or to
the long-context model (large documents). A short input that carries a table (HTML, ARIA,
Markdown/GFM, CSV or TSV) goes to the long-context model too, which keeps rows apart: slower,
and the summary ends with a warning naming the format; `LOCAL_DELEGATE_SUMMARIZE_TABLE_LONG=0`
turns this off.

Args:
    text: Text to summarize (use this or 'path').
    path: Path to a file whose content is summarized (read server-side).
    max_words: Maximum length of the summary in words.
    focus: Optional. What you care about in the document (e.g. "configuration figures",
        "risks"): the summary prioritizes it and keeps its concrete data verbatim.

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": "local_summarize"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
textNo
focusNo
max_wordsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.32.0
    • addedInput schema / properties / focus
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Focus"
      +}
  2. First observedv0.2.0

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the readOnly/openWorld annotations by disclosing model routing (mechanical vs long-context), a table-detection quirk that changes latency and appends a format warning to the result, and the environment variable that disables it. It falls just short of full disclosure because it does not say what happens when the local model fails or when neither input argument is supplied.

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?

Front-loads the highest-value guidance (the preference rule) before the mechanics, and nearly every sentence carries information an agent needs. The table-routing paragraph is dense and somewhat niche, but it is genuinely conditional behavior rather than filler.

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?

For a four-parameter local delegation tool with an output schema, this covers routing, context savings, and length control adequately, and the appended warning behavior is disclosed even though return values need not be explained. The main gap is the undefined case where neither 'text' nor 'path' is provided.

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 description coverage is 0%, so the description carries the burden, and its Args section gives meaning for all four parameters, including a concrete example for 'focus' and the effect of 'max_words'. It loses a point for omitting the max_words default (150) and for not stating the behavior when both 'text' and 'path' are null, which is possible since nothing is required.

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 ('Summarizes text or the content of a file with a local model') and explicitly differentiates itself from the sibling read path that would otherwise load content into context. An agent can identify the tool's job and its scope from the first sentence alone.

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 an explicit selection rule: prefer this over Read when the file is large (>200 lines / >10 KB) and only a summary is needed. It also routes between the two input modes ('pass path' vs 'alternatively pass text'), so both the when-to-use and the when-not-to-use case are covered.

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