vulcan_execute_codeRuns custom Python code inside an active Vulcan session with vulcan and vulcan_gui preloaded, returning stdout, stderr, and structured JSON when you assign to result.
Execute custom Python code inside Vulcan's active session (vulcan and vulcan_gui preloaded).
Assign to result inside your snippet to return structured JSON values alongside stdout/stderr.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds real context beyond the lone `destructiveHint: true`: code runs inside an already-active session with two modules preloaded, and the `result` convention controls the return shape. However, it never warns that execution can mutate or corrupt live session state, gives no timeout/sandbox/error semantics — notable gaps for a tool flagged destructive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, zero waste, and the essential fact (executes in the active session with modules preloaded) is front-loaded before the return-value convention.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter code-execution tool with no output schema, the definition covers the environment and return convention but leaves the agent guessing on timeouts, whether session state persists across calls, how errors surface, and what 'destructive' means in practice.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and the single `code` parameter has no description at all, so the schema contributes nothing. The description partially compensates by defining the `result` assignment contract for structured JSON output alongside stdout/stderr, but says nothing about expected language constraints, snippet scope, or state persistence between calls.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource: executing custom Python inside Vulcan's active session, with the preloaded `vulcan`/`vulcan_gui` modules named. Sibling tools are all domain-scoped (design, triangulation, drillholes), so this reads as the escape hatch for arbitrary code, though the description never says so explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied rather than stated: an agent can infer this is for custom logic that the purpose-built `vulcan_*` tools don't cover, but there is no explicit 'use this when...' or 'prefer vulcan_design for X' routing. No exclusions, prerequisites, or guidance on when writing raw code is inappropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.