Skip to main content
Glama
mariusei

Scantool - File Scanner MCP

by mariusei
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Scan Directory

scan_directory

Scan a directory to get a file tree with one-line summaries, code health, and churn labels for efficient codebase exploration.

Instructions

Skeleton of files or a directory: every structure with path:line, signature or title, a condensed excerpt within the budget. A directory gives the tree with one-line gists. --depth quick is about 300 tokens per file, normal 1500, deep everything with module values whole (files only). Elided content is marked ⟨…⟩ +N; focus reads it. A directory: the file tree with one-line gists per file, code health and churn labels; ref= reads it at a git ref. Replaces Glob/ls for all file types. In your shell: sct scan <dir> (if sct is not on PATH, "/app/.venv/bin/python" -m scantool.cli replaces sct).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
refNo
modeNobalanced
deltaNo
depthNo
callerNo
patternNo**/*
directoryYes
max_filesNo
output_formatNotree
exclude_patternsNo
include_metadataNo
respect_gitignoreNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.26.0
    • addedInput schema / properties / ref
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  2. Changed2 schema fields changedv0.23.0
    • addedInput schema / properties / caller
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
    • addedInput schema / properties / include_metadata
      Added value: +{
+  "default": true,
+  "type": "boolean"
+}
  3. Changed1 schema field changedv0.20.1
    • addedInput schema / additionalProperties
      Added value: +false
  4. First observedv0.19.4

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden. It is transparent about key output behaviors: depth-specific token budgets (~300/1500/whole), elision markers (⟨…⟩ +N), one-line gists, code health/churn labels, and reading a specific git ref. It stops short of stating that the operation is read-only, but the core output behavior is well covered.

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

Conciseness3/5

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

The description is dense but unstructured, mixing output format, depth rules, elision markers, and a shell command in one unparagraphed block. It repeats the directory-tree statement twice ('A directory gives the tree with one-line gists' vs 'A directory: the file tree with one-line gists per file...'). The shell snippet is useful but tangential, and the prose could be tightened into clearer sections.

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

Completeness2/5

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

For a tool with 12 parameters, no output schema, and no annotations, the description is under-specified. It explains skeleton/tree output and covers `depth` and `ref`, but an agent cannot determine the semantics of `mode`, `delta`, or `caller`, or the allowed values of `output_format`. The lack of return-format guidance beyond the elision markers makes it hard to parse results reliably.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

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 explains `depth` and `ref`, and indirectly hints at `include_metadata` via 'code health and churn labels.' However, it leaves `mode`, `delta`, `caller`, `max_files`, `output_format`, `exclude_patterns`, `respect_gitignore`, and `pattern` unexplained; opaque params like `delta` and `caller` remain ambiguous. The description does not carry the weight needed for this low-coverage schema.

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 what the tool produces: a structure skeleton with path:line, signature/title, and condensed excerpt, plus a directory tree with one-line gists and metadata labels. It also differentiates itself by claiming to replace Glob/ls for all file types. However, it never explicitly names sibling tools like list_directories or preview_directory, so differentiation relies on inference.

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?

The description gives a clear context of use: it replaces Glob/ls for all file types, signaling when an agent should reach for this rather than a simple listing. It also offers depth-mode and ref options as practical usage hints. Yet it provides no explicit 'when not to use' guidance or direct comparison to sibling tools such as scan_file_content or preview_directory.

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