Skip to main content
Glama
agentic-search-mcp

agentic-search-mcp

glob

Find files and directories that match a pathlib-style pattern, optionally within a specific search root and with a cap on returned matches.

Instructions

Find files and directories matching a glob pattern.

Args: pattern: A pathlib-style glob, e.g. **/*.py or src/**/*.ts. path: Directory to search within (absolute or root-relative, default root). max_results: Cap on returned matches (default 1000).

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": {
      "pattern": "<pattern>"
    },
    "name": "glob"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo.
patternYes
max_resultsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
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 behavioral burden. It does disclose that matches include both files and directories and that results are capped by max_results, which is useful beyond the schema. It does not say whether the cap silently truncates, whether hidden files or symlinks are followed, whether results are ordered, or what happens when the directory does not exist.

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?

The purpose sentence is front-loaded as a single line, followed by a compact Args block that mirrors the parameter order. Every line carries information the schema lacks; there is no filler.

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

Completeness3/5

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

An output schema exists, so return shape need not be explained, and all three otherwise-undocumented parameters are covered. However, for a filesystem search tool with no annotations, truncation behavior, error behavior, and hidden-file/symlink handling are gaps that leave an agent guessing about edge cases.

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 this section does real work: it explains the glob syntax with two concrete pattern examples, clarifies that path may be absolute or root-relative with the root as default, and states the max_results default. Remaining gaps are edge-case semantics such as case sensitivity, brace expansion, and separator handling.

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?

States a specific verb ('Find') and resource ('files and directories') plus the matching mechanism (glob pattern), which is unambiguous on its own. It does not name or contrast with the siblings grep or read, so an agent must rely on prior knowledge to know that content search is grep's job and file reading is read's job.

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 by the purpose statement — there is no 'use this when you need to locate files by name rather than by content' guidance and no pointer to grep/read as alternatives. The path and max_results docs hint at scoped search, but nothing tells the agent when glob is the wrong tool.

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