Skip to main content
Glama
Sign In

OrgLines

by com.orglines
OverviewDiscussionsAdmin

Set workspace AI instructions

set_workspace_instructions
Destructive

Set THIS workspace's custom AI instructions (TZ-021) — markdown, up to 4KB. They are delivered in the MCP initialize instructions to EVERY connected client of the workspace (any model, any window) so a fresh session inherits how the owner wants their workspace run. OWNER-ONLY: only the workspace owner may set them (others are forbidden). Over MCP this runs the platform's propose→confirm write gate. Pass the FULL new text in 'instructions' — it REPLACES the previous value (pass an empty string to clear it). This text is user-provided and can never override the gateway's security/confirm rules. Use get_workspace_protocol to read the current protocol. CONFIRMATION: this tool is PROPOSED, never performed directly. You get status='confirmation_required' with an action_id and a plan_token, and the write happens only after confirm_action.

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": {
      "instructions": "<instructions>"
    },
    "name": "set_workspace_instructions"
  }
}

Input Schema

NameRequiredDescriptionDefault
instructionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations: describes the propose→confirm write gate, the blast radius (every connected client of the workspace inherits the text), the owner-only authorization, and that this text cannot override gateway security rules. It also names the exact confirmation response shape (status='confirmation_required' with action_id and plan_token) that annotations cannot express.

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-loads the core action, then authorization, replacement semantics, safety note, and confirmation flow in a logical order. Dense but nearly every sentence carries operational information; the parenthetical TZ-021 reference adds little for an agent.

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?

No output schema exists, yet the description supplies the return contract (status, action_id, plan_token) and the follow-up path via confirm_action. For a destructive, confirmation-gated mutation this is as complete as an agent needs to call and follow through correctly.

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?

With 0% schema description coverage the description must carry the parameter, and it does: full new text, replaces rather than appends, empty string clears. Minor penalty for stating a 4KB limit while the schema's maxLength is 8192 characters, an ambiguity the agent could hit at the boundary.

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 ("Set THIS workspace's custom AI instructions"), scopes it to the current workspace, and adds distinguishing detail (markdown, size limit, delivered via MCP initialize) that separates it from get_workspace_protocol and generic set_* siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: read current protocol with get_workspace_protocol, owner-only access with others forbidden, and full replacement semantics with an empty string to clear. When-to-use, who-may-use, and the alternative read tool are all named rather than implied.

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

All OrgLines toolsInspect
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