Skip to main content
Glama

run_circuit

Runs the circuit built with build_circuit and circuit_step, on the lab's engine, over three years at most, and keeps it as the person's project, so its report's Open in the lab puts the same circuit on the canvas. The window lights up card by card as it runs and the result appears under it. get_primitives_run_progress follows it by its task_id; when the run has finished it answers with the result and report_url, the run's report. Every account runs it within a daily allowance; a refused call does not count. A circuit asked for more than three years runs three, and held says so in one line: a longer test runs in the lab.

    Args:
        name: Optional. The project's name in the person's words, when the circuit has none yet.
        question: Optional. One sentence restating what the run should answer, not the person's message: the
            title of the report, and kept only as that.
    

Input Schema

NameRequiredDescriptionDefault
nameNo
questionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: a daily per-account allowance where a refused call does not count, silent truncation of windows beyond three years with a `held` note, persistence of the run as the person's project, UI cadence while running, and the presence of a result plus report_url. Annotations only cover safety flags, so this is real added value.

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?

Purpose and constraints are front-loaded, and most sentences carry load-bearing information (cap, quota, progress tool, param meanings). A few narrative asides, such as the window lighting up card by card, are marginal but not distracting.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and only two optional params, the description does the heavy lifting: it explains the run's lifecycle, the progress-tracking sibling, the terminal result and report_url, and truncation behavior. Remaining ambiguity is around the exact shape of the `held` response, which is only described as 'one line'.

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 carry both optional params, and it does: `name` is the project name in the person's words used only when the circuit lacks one, and `question` is a one-sentence restatement (explicitly not the raw user message) that becomes the report title and is kept only as that. The guidance is semantically rich but slightly indirect in wording.

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 ('runs the circuit built with build_circuit and circuit_step') and names the build-side siblings it depends on, so an agent can distinguish it from build_circuit/circuit_step and from the generic start_* runners. The scope ('on the lab's engine, over three years at most') further pins down what kind of run this is.

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?

Gives a clear prerequisite (the circuit must already exist via build_circuit and circuit_step) and routes progress polling to get_primitives_run_progress. It notes the three-year cap and that longer tests run in the lab, but never explicitly contrast it with look-alike siblings such as start_test or start_primitives_run.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources