Skip to main content
Glama
Sign In

Vibes-Coded Agent Tools

by io.github.doteyeso-ops
OverviewDiscussionsAdmin

vc_workspace_write

Read-onlyIdempotent

Write state into a private workspace (member only).

Agent A works and writes state; agent B (fresh context) reads it and continues.
This is the durable handoff — survives context loss. Only workspace members
can write; outsiders get allowed:false.
Sibling: vc_workspace_read, vc_workspace_list.

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": {
      "workspace_id": "<workspace_id>",
      "member_key": "<member_key>",
      "note_key": "<note_key>",
      "content": "<content>"
    },
    "name": "vc_workspace_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
contentYesState to store — JSON object or text.
note_keyYesNote key within the workspace, e.g. task-state.
member_keyYesYour agent identity (creator or partner).
workspace_idYesWorkspace id returned by vc_workspace_create.
payment_signatureNoOptional x402 PAYMENT-SIGNATURE if not using X-Vibes-Key.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior1/5

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

This is an Annotation Contradiction. The description repeatedly claims a persistent write operation ('Write state', 'writes state', 'Only workspace members can write'), while annotations declare readOnlyHint: true. An agent cannot trust whether calling this tool actually mutates state, which overrides the otherwise useful member-only and allowed:false context.

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 core action is front-loaded in the first sentence, and the remaining sentences each add value: use case, durability, permission behavior, and sibling routing. The description is compact and scannable, with no filler or irrelevant detail.

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?

The description covers the durable handoff use case, member restrictions, and sibling tools, while the schema and output schema cover parameters and return values. However, the readOnlyHint contradiction introduces fundamental ambiguity about whether the tool has a write side effect, so the full tool contract is not complete enough for an agent to act with confidence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes every parameter at 100% coverage, including member_key as agent identity and content as JSON object or text. The description adds permission and durability context, which reinforces member_key and content meaning, but it does not provide additional format, constraint, or syntax details beyond the schema. The baseline of 3 is appropriate.

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 first sentence states the exact operation and target: 'Write state into a private workspace (member only).' This clearly distinguishes it from vc_workspace_read and vc_workspace_list, which are explicitly listed as siblings. The durable handoff explanation reinforces that this tool persists state rather than retrieving it.

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?

The description gives a concrete scenario ('Agent A works and writes state; agent B (fresh context) reads it and continues') and states the durability property ('survives context loss'). It lists the read/list siblings and warns that non-members will receive allowed:false. It stops short of explicitly saying 'use vc_workspace_read to retrieve', but the routing is easy to infer.

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

All Vibes-Coded Agent Tools 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