Execute SPICE simulation on a given setup path, returning results synchronously or via managed job.
Run SPICE simulation on a Setup. The gateway executes it synchronously on IC-CAP's main thread; external MCP clients may submit it as a managed job.
| Name | Required | Description | Default |
|---|---|---|---|
| run_async | No | Reserved for broker-managed jobs; direct gateway calls must use false | |
| setup_path | Yes | Setup path |
Changes observed during successful MCP inspections.
v0.2.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses synchronous execution on IC-CAP's main thread, which implies blocking behavior and main-thread coupling, and notes the managed-job path for external clients. It does not mention side effects or return behavior, but this is still meaningful transparency beyond the schema.
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 sentences, no filler, with the core purpose front-loaded and behavioral context in the second sentence. Every clause adds distinct information needed for correct invocation.
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 simple 2-parameter tool with one required parameter and no output schema, the description covers what the tool does and how it executes. It omits post-conditions such as what happens to simulation results, but the essential invocation details are present.
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?
The input schema already describes both parameters, including run_async's reservation for broker-managed jobs, at 100% coverage. The description adds no parameter-level detail beyond what the schema provides, so the baseline of 3 applies.
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?
The description uses a specific verb and resource: 'Run SPICE simulation on a Setup.' It clearly distinguishes this from measurement or transform tools in the sibling list by naming the exact operation (SPICE simulation) rather than a generic 'run' or 'execute'.
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?
The description gives clear invocation context: synchronous execution on IC-CAP's main thread and managed-job submission for external MCP clients. It does not explicitly name alternatives like setup_measure or iccap_job_submit, but the execution-mode guidance is concrete and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.