Skip to main content
Glama

driftguard_compress_log

Compresses verbose build logs and stack traces by stripping ANSI colors, node_modules boilerplate, and internal noise, reducing context tokens for AI coding agents.

Instructions

Comprime log di compilazione prolissi e stack trace (rimuovendo ANSI colors, boilerplate di node_modules e rumore interno), risparmiando fino all'85-90% di token di contesto.

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": {
      "rawLog": "<rawLog>"
    },
    "name": "driftguard_compress_log"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawLogYesL'intero output del comando terminale da comprimere.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose the important behavioral trait that the transformation is lossy (specific categories of content are removed) and quantifies the token reduction at 85-90%. However, it says nothing about what happens with non-log input, size limits, or the shape of the returned compressed text.

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?

One front-loaded sentence with a tight parenthetical enumerating the removed noise and a quantified payoff. Nothing is redundant or padded.

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 single-parameter, side-effect-free transformation with no output schema, the description adequately conveys what goes in and what effect results. The remaining gap is the return format and edge-case behavior, but that is minor at this complexity level.

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% and the single parameter already documents that the entire terminal output is expected. The description adds no syntax, sizing, or formatting detail beyond what the schema states, so the baseline of 3 applies.

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 names a specific verb (comprime) and concrete resources (compilation logs and stack traces), then enumerates exactly what is stripped (ANSI colors, node_modules boilerplate, internal noise). No sibling tool in the driftguard set compresses logs, so the agent can select it unambiguously.

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?

Usage is only implied: the token-saving benefit suggests it should be used before feeding large terminal output into context, but the description never states when to use it, when not to, or what to do with the alternative of passing raw logs. With no competing sibling there is no routing risk, but the guidance is inference rather than instruction.

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