lightbulb-mcp

by RPasquale

Overview Schema Source Related Servers Discussions Admin

Python

Remote

code_workspace_chat

Send a message to a code workspace to request code writing, command execution, or file analysis.

Instructions

Send a message to a code workspace — ask it to write code, run commands, analyze files.

Args: workspace_id: The workspace ID to interact with message: Your instruction or question action: Optional coding action such as chat, explain_code, or propose_changes. propose_changes is normalized to preview chat mode for backend compatibility. coding_harness: Required when the message starts a new consulting project. conversation_id: Optional conversation/thread ID for continuity active_file: Optional active file path to bias the coding agent history: Optional JSON array of prior chat messages attachments: Optional JSON array of attachments context: Optional JSON object with structured coding context policy: Optional JSON object with workspace policy overrides preview_mode: If true, return proposed changes without mutating files auto_push: If true, allow the coding run to auto-push after verification max_tool_loops: Agent tool-loop turn ceiling, including its internal mutation retry (4-48). This is not an exact token or dollar cap. max_cost_usd: Optional provider cost ceiling for this request (0.01-1000). Claude enforces it in-turn; runtimes without a native cost cap fail closed on automatic retries. max_total_tokens: Optional provider token ceiling for this request (1-2000000). Enforcement capability is reported in the response budget receipt.

Input Schema

TableJSON Schema

Name	Required	Default
`action`	No	chat
`policy`	No	{}
`context`	No	{}
`history`	No	[]
`message`	Yes
`auto_push`	No
`active_file`	No
`attachments`	No	[]
`max_cost_usd`	No
`preview_mode`	No
`workspace_id`	Yes
`agent_model_id`	No
`coding_harness`	No
`max_tool_loops`	No
`conversation_id`	No
`idempotency_key`	No
`max_total_tokens`	No
`agent_model_profile_id`	No
`agent_model_selection_id`	No
`agent_provider_connection_id`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.1.1Sep 7, 2026

addedInput schema / properties / coding_harness

Added value: +{
+  "default": "",
+  "title": "Coding Harness",
+  "type": "string"
+}

addedInput schema / properties / max_cost_usd

Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Max Cost Usd"
+}

addedInput schema / properties / max_tool_loops

Added value: +{
+  "default": 8,
+  "title": "Max Tool Loops",
+  "type": "integer"
+}

addedInput schema / properties / max_total_tokens

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Max Total Tokens"
+}

First observedv0.1.0Jun 25, 2026

TDQS

A3.5/5.0

Behavior4/5

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

With no annotations, the description carries the behavioral disclosure burden and does a strong job: it explains preview_mode prevents file mutation, auto_push can push after verification, propose_changes is normalized to preview chat mode, and cost ceilings behave differently across runtimes. It stops short of disclosing permission requirements or reversibility, but the side-effect and safety-relevant behavior is well covered.

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 description is front-loaded with the core action and then organized as a parameter list. Every listed detail is informative and not redundant with schema text, and the caveats are compact. It is long, but the 20-parameter surface justifies the length.

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 provides enough to call the tool correctly for the common path, including key optional controls around cost, tokens, and mutation. However, it omits several schema parameters that may matter in advanced use, and it does not situate the tool among closely related code_workspace_* and coding_* siblings, leaving an agent to infer how to coordinate runs, retrieval, and alternatives.

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 description coverage is 0%, so the description must compensate, and it meaningfully does for 15 of 20 parameters. It adds ranges, defaults, conditions, and behavioral caveats far beyond the schema, e.g., 'not an exact token or dollar cap', 'fail closed on automatic retries', and the propose_changes normalization. However, five parameters such as idempotency_key and agent_model_* are left unexplained.

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 clearly states a specific action ('Send a message to a code workspace') and enumerates representative capabilities such as writing code, running commands, and analyzing files. It is distinguishable from generic tools, though it does not explicitly differentiate itself from close siblings like coding_chat or coding_run_command.

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

Usage Guidelines2/5

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

No guidance is given for when to choose this tool over alternatives such as coding_chat, coding_run_command, or code_workspace_get_run. The only conditional usage note is that coding_harness is required for a new consulting project, which is parameter-level guidance rather than tool-selection guidance.

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

Deploy Server