Skip to main content
Glama
Sign In
Puppet Master

Puppet Master

by khr898
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

puppet_read

Read, search, or summarize files and logs to get a short answer with claims mechanically verified against cited source lines; use it to find code or evidence without opening files yourself.

Instructions

USE THIS FIRST to read, search or summarize files/logs instead of opening them yourself. Returns a short answer whose claims are mechanically verified against the source (unverified claims are removed). Before acting on a claim, read its cited lines yourself. Pass files, path:start-end ranges or globs (e.g. /repo/src/**/*.py), never directories. Anything over one chunk is searched: Flint sees only the blocks that best match the question, and focus in the report says how much it saw. Use it to find code instead of grepping. exhaustive=true reads everything instead: ≤10k tokens of file per chunk, ≤8 chunks. Not for drafting prose (use puppet_ask).

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": {
      "paths": "<paths>",
      "question": "<question>"
    },
    "name": "puppet_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathsYes
questionYes
exhaustiveNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so well: it discloses that claims are mechanically verified against source, unverified claims are stripped, over-chunk inputs are searched rather than fully read, and exhaustive mode has explicit chunk and token limits. These are exactly the behavioral traits an agent needs to interpret results correctly.

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-loaded with the primary directive ('USE THIS FIRST'), then behavior, then parameter guidance, then the sibling exclusion. Dense and mostly efficient, though the long middle sentence about chunking and focus packs several ideas together and is slightly run-on.

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 tool with no annotations and no output schema, the description is nearly complete: it explains the return format (a short answer with cited lines), the verification behavior, and the focus report. It leaves the exact shape of the focus report slightly vague, but nothing essential for correct invocation is missing.

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 must compensate; it does for two of three parameters, explaining that paths accepts files, path:start-end ranges and globs but never directories, and describing exhaustive=true semantics and limits. The question parameter is only implicitly referenced, not explicitly defined, keeping this just short of a 5.

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 set (read, search, summarize) and resource (files/logs), and distinguishes itself from siblings by telling the agent to use it first instead of opening files or grepping. It also names puppet_ask as the alternative for drafting prose, so the boundary is clear.

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?

Explicitly says when to use it (first, instead of reading files yourself, instead of grepping), when not to (not for drafting prose — use puppet_ask), and how to choose the exhaustive flag. No when-to-use decisions are left to inference.

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

Deploy Server

Other Tools