Skills MCP Server

Overview Schema Source Related Servers Discussions Admin

a11y_set_workspace

Set the project folder the file editor can read and edit, preventing access outside it. Use only the folder the user names; ask if unknown and never guess.

Instructions

Choose the project folder the file editor may touch. Use ONLY the folder the person named in the conversation (ask them if you do not know it); never guess. Nothing outside it can be read or edited, and the root of the disk or the whole home folder is refused. Nothing to configure beforehand: this is the only setup, and it happens inside the conversation.

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": "a11y_set_workspace"
  }
}

Input Schema

Name	Required	Description	Default
`path`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.1.0Oct 19, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and discloses real behavior: nothing outside the chosen folder is readable or editable, and disk root / whole home are refused, plus there is no pre-configuration. It omits edge behavior (e.g., whether the folder must exist, what happens on an invalid/relative path), keeping it from a 5.

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 core purpose, then the sourcing rule, then the sandbox boundary. Three compact sentences with no filler, though the run-on construction of the middle sentence slightly reduces readability.

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 one-parameter setup tool with an output schema, the description covers purpose, sourcing rule, and sandbox limits, which is enough for an agent to call it correctly. Return-value details are delegated to the output schema, which is appropriate.

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 0% for the single 'path' parameter, so the description must compensate. It does by specifying the path must be an actual folder named by the user and by constraining forbidden values (root, whole home), adding meaning beyond the bare string schema.

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 and resource: 'Choose the project folder the file editor may touch.' The scope is precise enough that the agent knows this is the workspace-scoping step that gates the sibling file tools (a11y_read_file, a11y_edit_file, a11y_list_content), even though it doesn't name them.

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?

Explicit guidance on when and how: use only the folder named by the person, ask if unknown, never guess. It also frames this as the sole setup step occurring in-conversation. It doesn't name any alternative tool or exclusion, so it falls short of a 5, but the usage rules are unusually clear.

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