MeshMind

Crush a file to a token budget

crush_file

Reads and compresses oversized local files to fit a token budget, auto-escalating compression until the output meets the target. Returns compressed content, token savings, and a reversible reference.

Instructions

Shortcut for the common 'this file is too big to read' case: reads a local file and compresses it in one call. With targetTokens, auto-escalates the pipeline until it fits; otherwise applies the default lossless-ish pipeline. Returns the compressed payload, exact BPE savings, and a reversible ref.

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": {
      "path": "<path>"
    },
    "name": "crush_file"
  }
}

Input Schema

Name	Required	Description
`path`	Yes	Local file to read and compress.
`targetTokens`	No	Token budget — auto-escalate until output fits.
`mode`	No	Compression regime (default auto).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Jun 17, 2026

TDQS

A4/5.0

Behavior4/5

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

No annotations provided, so the description carries full burden. It discloses auto-escalation behavior, default lossless-ish pipeline, return payload, BPE savings, and reversible ref. Does not cover auth, size limits, or side effects, but provides sufficient behavioral context for safe invocation.

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?

Three sentences, front-loaded with purpose, each sentence adds distinct value. No wasted words.

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?

Given no output schema and three parameters, the description explains the main use case, optional behaviors, and return values. Lacks file type support notes but is sufficient for typical use.

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 coverage is 100% with good parameter descriptions. The tool description adds context about auto-escalation for targetTokens, but largely overlaps with schema. Baseline 3 is appropriate.

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 description clearly states the verb ('reads and compresses') and the resource ('local file'), and positions it as a shortcut for 'this file is too big to read'. It distinguishes from siblings by focusing on compression, which is not covered by other tool names.

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

Usage Guidelines3/5

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

The description explains the typical use case (too-big file) and the auto-escalation behavior with targetTokens, but does not explicitly state when NOT to use the tool or mention alternatives among siblings.

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

Deploy Server