Skip to main content
Glama

List a directory on a QNX target

file_list
Read-onlyIdempotent

Lists directory contents on a QNX target read-only, including names, types, sizes, modes, mtimes, and symlink targets, with max-entry limits and truncation status.

Instructions

List one directory on the target, read-only: name, type (file, dir, symlink, char, block, fifo, socket, other), size, mode, mtime and, for symlinks, where they point (links are described, never followed; the directory itself may be reached through a link, real_path says where it is). Entries are sorted by name; at most max_entries are returned, total_entries counts all of them and truncated says whether some were left out. path must be absolute and normalised (no '.', '..', '//' or trailing '/'); '/' lists the root.

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": {
      "target": "<target>",
      "path": "<path>"
    },
    "name": "file_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute directory on the target, e.g. /data/var/dumper or /tmp
targetYesTarget name such as 'tb' (lowercase letters, digits, '-', '_'); must be inside the server allowlist
max_entriesNoMaximum entries returned (the first ones by name)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still earns credit by adding non-obvious behavior: symlinks are described and never followed, the directory itself may be reached through a link with real_path reporting it, and results are sorted by name with truncation flagged. Only the error behavior for an invalid target or non-existent path is left unstated.

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?

The content is front-loaded and every clause carries information, but it is delivered as one very dense sentence with stacked parentheticals that takes effort to parse. Slight structural improvement would be to split the symlink and truncation clauses out.

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

Completeness5/5

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

For a three-parameter, read-only listing tool this covers everything an agent needs: legal input form, sort order, paging/truncation contract, and symlink handling. An output schema exists, yet the description still names the key return fields, leaving no ambiguity about what a call yields.

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 coverage is 100%, so the baseline is 3, and the description goes beyond it: it constrains path to absolute normalised form with no '.', '..', '//' or trailing slash, explains that '/' lists root, and clarifies that max_entries returns the first entries by name. That is meaningful added semantics over the field descriptions.

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 opens with a specific verb and resource ('List one directory on the target, read-only') and enumerates exactly what comes back: name, type, size, mode, mtime, symlink destinations. That precision clearly separates it from file_get and file_put among the siblings.

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 implied rather than stated: it's a single-directory, non-recursive listing, and the path rules (absolute, normalised, '/' for root) tell the agent what input is legal. However, it never says when to prefer this over file_get for inspecting a file, nor does it name any alternative or exclusion.

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