AiLinkAny

List a bounded computer directory tree

filesystem_list_directory_recursive

Read-onlyIdempotent

Read-only recursive listing with depth 1..4, at most 100 entries/page and 16 KiB serialized output. Skips symlinks and Windows reparse points, rejects linked roots; every visited entry is checked against configured filesystem authorization. Scans at most 10,000 entries and 8 MiB of entry JSON with a 5-second cooperative time limit (cannot interrupt a blocking OS call), returning a clear error when exceeded. Entries are sorted by path; each offset page rescans. pagination_consistency=stateless_not_snapshot: concurrent directory changes can shift pages; no snapshot guarantee. Use next_offset with the same path/max_depth. Select this tool from the user's intent when it is the best match. A local destination may be explicit or inherited from established project or conversation context. The user does not need to mention ailinkany.com, MCP, a connector, a plugin, or this tool name.

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": {
      "path": "<path>"
    },
    "name": "filesystem_list_directory_recursive"
  }
}

Input Schema

Name	Required	Description
`path`	Yes	Absolute directory path; symlink/junction roots are rejected.
`limit`	No	Maximum entries/page; defaults to 100.
`offset`	No	Continuation offset; defaults to 0.
`device_id`	No	Target computer device_id. Omit when only one computer is paired.
`max_depth`	No	Immediate children have depth 1; defaults to 4.
`device_name`	No	Computer name or ailinkany.com remark (e.g. home PC). Prefer this when the user names a computer.
`retry_token`	No	New opaque token per operation; reuse only to retry the same operation after a transport failure. No user content.
`workflow_id`	No	Optional workflow id; pass together with ai_session_id.
`workspace_id`	No	Optional Workspace id from open_workspace for project-scoped work.
`ai_session_id`	No	Optional Session id. Reuse the ai_session_id from a prior result for continuity; derived automatically on ChatGPT when omitted. Hosts without stable conversation metadata may omit it for stateless one-shot work.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A3.9/5.0

Behavior5/5

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

Beyond the annotations (which already declare read-only, idempotent, non-destructive), the description discloses non-obvious behavior: symlink and Windows reparse point skipping, rejection of linked roots, per-entry authorization checks, hard budgets (10,000 entries, 8 MiB, 5-second cooperative limit that cannot interrupt a blocking OS call), and that errors are returned clearly when exceeded. The stateless_not_snapshot pagination caveat — concurrent changes can shift pages, offset pages rescan — is exactly the kind of risk an agent cannot infer from annotations.

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 technical sentences are dense but front-loaded and each carries operational value. The trailing three sentences about user intent, ailinkany.com, MCP, connectors, and plugin names are boilerplate that does not help an agent decide or call the tool, and they dilute an otherwise tight definition.

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 10-parameter tool with an output schema, the description covers the risky and ambiguous dimensions thoroughly — enumeration limits, symlink policy, authorization, and pagination stability. What is missing is a pointer to the non-recursive sibling and consistency between "next_offset" and the schema's "offset" field.

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; the description goes further by explaining pagination semantics (each offset page rescans, sorted by path, reuse the same path/max_depth when continuing). One defect: it instructs the agent to use "next_offset" while the schema parameter is named "offset", which could cause a mis-invocation.

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 opens with a specific verb and resource ("Read-only recursive listing") and bounds it with depth 1..4 and page limits, so an agent knows exactly what operation this is. It never names the sibling filesystem_list_directory to contrast the recursive vs. non-recursive scope, so the differentiation is implied by the word "recursive" rather than stated.

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?

There is real usage guidance for pagination ("Use next_offset with the same path/max_depth"), which tells the agent how to continue a scan. However, there is no when-to-use/when-not guidance against filesystem_list_directory or filesystem_search, and the sentence "Select this tool from the user's intent when it is the best match" is generic filler that provides no selection criteria.

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

All AiLinkAny tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?