Skip to main content
Glama

thetacog-pmu-inspect

Inspect and control the PMU XOR→ClaudBridge pipeline by reading or writing pipeline state. Manage intent, reality, thresholds, trigger runs, and retrieve receipts.

Instructions

Inspect and control the PMU XOR→ClaudBridge pipeline. Reads/writes data/pmu/pipeline/state.json (shared with the CLI driver, dashboard, and ClaudBridge mock). Use to: peek current intent/reality + last run sigma/friction (get-state), change inputs (set-intent, set-reality, set-threshold), trigger a full pipeline run end-to-end (run; optional stage to stop early), retrieve a specific run's receipt (get-run), list recent runs (list-runs), or inspect the cached axis/tile libraries (list-axes, list-tiles). The intent/reality control plane is the load-bearing surface — changing intent here makes the next run + dashboard render against the new coordinate without code edits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
mixNoFor set-intent/set-reality: a mix spec { base:"A1,A1", drift:"B2,B2", drift_fraction:0.30 }
kindNoOptional input kind override for set-intent/set-reality: "coord" | "text" | "file"
limitNoFor list-runs / list-axes / list-tiles: max items returned
stageNoFor run: stop after this stage. Order: resolve → sense → sigma → binarize → project → xor → claudbridge
valueNoFor set-intent/set-reality: a coord like "A1,A1" or free text. For set-threshold: a number or "adaptive".
actionYesSubcommand
offsetNoFor list-tiles: pagination offset into the 20,736-tile library
run_idNoFor get-run: the run id to fetch (e.g., "run-2026-05-27T15-00-34-…")
thresholdNoFor run: override the binarize threshold ("adaptive" or a numeric like "0.55")
Behavior4/5

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

With no annotations, the description carries full burden. It discloses read/write access to a specific JSON file, the shared nature with other components, and the effect of each action (e.g., 'change inputs', 'trigger a full pipeline run', 'retrieve a receipt'). Missing details on destructiveness of 'reset' or concurrency implications, but generally sufficient.

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 moderately concise, front-loading the main purpose. It lists actions in a bullet-like format. Could be slightly tighter, but effective.

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?

Given 9 parameters and no output schema, the description explains what each action does but does not describe return formats for actions like run, get-run, or list-runs. The shared state context is helpful, but the agent would need to infer outputs from action names.

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

Parameters5/5

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

Schema coverage is 100%, yet the description adds substantial meaning beyond the schema: explains the mix object structure, stage order, threshold values, and kind override. Every parameter gets contextual explanation that helps an agent form correct input.

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 description clearly states the tool inspects and controls the PMU XOR→ClaudBridge pipeline, lists all 10 specific actions, and mentions the shared state file. It distinguishes the tool from siblings by focusing on pipeline state manipulation.

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

Usage Guidelines3/5

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

The description provides usage context for each subcommand ('Use to:'), but does not explicitly guide when to choose this tool over siblings like pmu_verify or thetacog-detect. No when-not-to-use or alternative naming.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/wiber/thetacog-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server