Skip to main content
Glama

tokenpull_compare

Read-only

Compares token usage across four local sources side-by-side, shows delta percentages against a baseline, and computes cascade scores to validate numbers or explain discrepancies.

Instructions

Pull token usage from ALL four local sources in parallel — tokenpull (JSONL canon), ccusage CLI, token-dashboard SQLite, and tokscale report — and return them side-by-side with delta % vs tokenpull as the baseline. Also computes the cascade (Υ, SNR, Leverage, class) for each source so you can see how each verifier scores. Useful for validating your numbers before submitting, or understanding discrepancies between tools. Claude only for token-dash; codex and others use tokenpull + ccusage + tokscale. Token-only, on-device.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "tokenpull_compare"
  }
}

Input Schema

NameRequiredDescriptionDefault
platformNoplatform to compare (default: claude). token-dash and App only available for claude.

Output Schema

NameRequiredDescriptionDefault
sourcesNoSide-by-side comparison of each token source
platformNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.19.23
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "amp",
      -  "kimi",
      -  "qwen",
      -  "pi",
      -  "openclaw",
      -  "droid",
      -  "codebuff",
      -  "gemini",
      -  "copilot",
      -  "opencode",
      -  "goose",
      -  "kilo",
      -  "hermes",
      -  "devin",
      -  "other",
      -  "omp",
      -  "proxy",
      -  "antigravity",
      -  "grok",
      -  "zcode",
      -  "claude",
      -  "codex"
      -]New value: +[
      +  "amp",
      +  "kimi",
      +  "qwen",
      +  "pi",
      +  "openclaw",
      +  "droid",
      +  "codebuff",
      +  "gemini",
      +  "copilot",
      +  "opencode",
      +  "goose",
      +  "kilo",
      +  "hermes",
      +  "devin",
      +  "other",
      +  "omp",
      +  "proxy",
      +  "antigravity",
      +  "grok",
      +  "zcode",
      +  "cline",
      +  "claude",
      +  "codex"
      +]
  2. Changed1 schema field changedv0.19.15
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "amp",
      -  "kimi",
      -  "qwen",
      -  "pi",
      -  "openclaw",
      -  "droid",
      -  "codebuff",
      -  "gemini",
      -  "copilot",
      -  "opencode",
      -  "goose",
      -  "kilo",
      -  "hermes",
      -  "devin",
      -  "other",
      -  "omp",
      -  "proxy",
      -  "claude",
      -  "codex",
      -  "grok"
      -]New value: +[
      +  "amp",
      +  "kimi",
      +  "qwen",
      +  "pi",
      +  "openclaw",
      +  "droid",
      +  "codebuff",
      +  "gemini",
      +  "copilot",
      +  "opencode",
      +  "goose",
      +  "kilo",
      +  "hermes",
      +  "devin",
      +  "other",
      +  "omp",
      +  "proxy",
      +  "antigravity",
      +  "grok",
      +  "zcode",
      +  "claude",
      +  "codex"
      +]
  3. Changed1 schema field changedv0.19.7
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "amp",
      -  "kimi",
      -  "qwen",
      -  "pi",
      -  "openclaw",
      -  "droid",
      -  "codebuff",
      -  "gemini",
      -  "copilot",
      -  "opencode",
      -  "goose",
      -  "kilo",
      -  "hermes",
      -  "devin",
      -  "other",
      -  "omp",
      -  "proxy",
      -  "claude",
      -  "codex"
      -]New value: +[
      +  "amp",
      +  "kimi",
      +  "qwen",
      +  "pi",
      +  "openclaw",
      +  "droid",
      +  "codebuff",
      +  "gemini",
      +  "copilot",
      +  "opencode",
      +  "goose",
      +  "kilo",
      +  "hermes",
      +  "devin",
      +  "other",
      +  "omp",
      +  "proxy",
      +  "claude",
      +  "codex",
      +  "grok"
      +]
  4. Changed10 schema fields changedv0.19.6
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "amp",
      -  "kimi",
      -  "qwen",
      -  "pi",
      -  "openclaw",
      -  "droid",
      -  "codebuff",
      -  "gemini",
      -  "copilot",
      -  "opencode",
      -  "goose",
      -  "kilo",
      -  "hermes",
      -  "devin",
      -  "other",
      -  "claude",
      -  "codex"
      -]New value: +[
      +  "amp",
      +  "kimi",
      +  "qwen",
      +  "pi",
      +  "openclaw",
      +  "droid",
      +  "codebuff",
      +  "gemini",
      +  "copilot",
      +  "opencode",
      +  "goose",
      +  "kilo",
      +  "hermes",
      +  "devin",
      +  "other",
      +  "omp",
      +  "proxy",
      +  "claude",
      +  "codex"
      +]
    • changedOutput schema / properties / sources / items / properties / cascade / properties / class / description
      Previous value: -"Operator class tier"New value: +"Operator class tier (dev10x taxonomy)"
    • changedOutput schema / properties / sources / items / properties / cascade / properties / class / enum
      Previous value: -[
      -  "Burner",
      -  "Builder",
      -  "10xer"
      -]New value: +[
      +  "ARCH+ I",
      +  "ARCH+ II",
      +  "ARCH+ III",
      +  "ARCH I",
      +  "ARCH II",
      +  "ARCH III",
      +  "POWER I",
      +  "POWER II",
      +  "POWER III",
      +  "BASE I",
      +  "BASE II",
      +  "BASE III",
      +  "SEEKER I",
      +  "SEEKER II",
      +  "SEEKER III",
      +  "REFINER I",
      +  "REFINER II",
      +  "REFINER III",
      +  "BEARER I",
      +  "BEARER II",
      +  "BEARER III",
      +  "IGNITER I",
      +  "IGNITER II",
      +  "IGNITER III",
      +  "UNCLASSED"
      +]
    • addedOutput schema / properties / sources / items / properties / cascade / properties / dev10x
      Added value: +{
      +  "description": "10xDEV score (log10 of the cascade product)",
      +  "type": "number"
      +}
    • addedOutput schema / properties / sources / items / properties / cascade / properties / mode
      Added value: +{
      +  "description": "Detected working mode (BUILD/EDIT/DEBUG/MAINTAIN/IDLE) + confidence",
      +  "type": "object"
      +}
    • addedOutput schema / properties / sources / items / properties / cascade / properties / pillars
      Added value: +{
      +  "description": "The four raw token pillars the cascade was computed from",
      +  "type": "object"
      +}
    • removedOutput schema / properties / sources / items / properties / cascade / properties / tenx_dev
      Removed value: -{
      -  "description": "10xDEV score",
      -  "type": "number"
      -}
    • addedOutput schema / properties / sources / items / properties / cascade / properties / yield
      Added value: +{
      +  "description": "Υ Yield — the headline efficiency metric (Cache Reads × Output / Input²)",
      +  "type": "number"
      +}
    • removedOutput schema / properties / sources / items / properties / cascade / properties / yield_
      Removed value: -{
      -  "description": "Υ Yield — the headline efficiency metric (Cache Reads × Output / Input²)",
      -  "type": "number"
      -}
    • changedOutput schema / properties / sources / items / properties / cascade / required
      Previous value: -[
      -  "yield_",
      -  "class"
      -]New value: +[
      +  "yield",
      +  "class"
      +]
  5. Changed1 schema field changedv0.18.1
    • changedInput schema / properties / platform / enum
      Previous value: -[
      -  "amp",
      -  "kimi",
      -  "qwen",
      -  "pi",
      -  "openclaw",
      -  "droid",
      -  "codebuff",
      -  "gemini",
      -  "copilot",
      -  "opencode",
      -  "goose",
      -  "kilo",
      -  "hermes",
      -  "claude",
      -  "codex"
      -]New value: +[
      +  "amp",
      +  "kimi",
      +  "qwen",
      +  "pi",
      +  "openclaw",
      +  "droid",
      +  "codebuff",
      +  "gemini",
      +  "copilot",
      +  "opencode",
      +  "goose",
      +  "kilo",
      +  "hermes",
      +  "devin",
      +  "other",
      +  "claude",
      +  "codex"
      +]
  6. Changed1 schema field changedv0.16.0
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "platform": {
      +      "type": "string"
      +    },
      +    "sources": {
      +      "description": "Side-by-side comparison of each token source",
      +      "items": {
      +        "properties": {
      +          "cascade": {
      +            "properties": {
      +              "card": {
      +                "description": "Deterministic prose summary of the cascade result",
      +                "type": "string"
      +              },
      +              "class": {
      +                "description": "Operator class tier",
      +                "enum": [
      +                  "Burner",
      +                  "Builder",
      +                  "10xer"
      +                ],
      +                "type": "string"
      +              },
      +              "leverage": {
      +                "description": "Cr/I — cache reads divided by input",
      +                "type": "number"
      +              },
      +              "snr": {
      +                "description": "Signal-to-noise ratio",
      +                "type": "number"
      +              },
      +              "tenx_dev": {
      +                "description": "10xDEV score",
      +                "type": "number"
      +              },
      +              "velocity": {
      +                "description": "O/I — output divided by input",
      +                "type": "number"
      +              },
      +              "warnings": {
      +                "description": "Parse or data warnings if any",
      +                "items": {
      +                  "type": "string"
      +                },
      +                "type": "array"
      +              },
      +              "yield_": {
      +                "description": "Υ Yield — the headline efficiency metric (Cache Reads × Output / Input²)",
      +                "type": "number"
      +              }
      +            },
      +            "required": [
      +              "yield_",
      +              "class"
      +            ],
      +            "type": "object"
      +          },
      +          "delta_pct": {
      +            "description": "Delta % vs tokenpull baseline",
      +            "type": "object"
      +          },
      +          "pillars": {
      +            "type": "object"
      +          },
      +          "source": {
      +            "description": "Source name (tokenpull, ccusage, token-dash, tokscale)",
      +            "type": "string"
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "type": "object"
      +}
  7. Addedv0.6.10

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds real behavioral context: four local sources pulled in parallel, tokenpull treated as the delta baseline, cascade metrics computed per source, and per-platform source availability. It does not say how partial failures or missing sources are handled, which is the main remaining gap.

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?

Four sentences, front-loaded with the core action and baseline semantics before the secondary cascade and platform details. "Token-only, on-device" borders on restating openWorldHint=false, and the parenthetical source glosses add density, but nothing is truly wasted.

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?

This is a complex multi-source aggregation tool with one optional parameter, and an output schema exists so return values need no explanation. The definition covers sources, baseline, cascade output, and platform constraints; only failure/partial-availability behavior is unspecified, which is a minor omission.

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 coverage is 100% with an enumerated platform list, so the schema carries the baseline. The description still adds meaning by explaining that the platform value changes which sources are queried (token-dash only on claude) and that claude is the default path — information the schema does not state.

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?

"Pull token usage from ALL four local sources in parallel" names a specific verb, the exact resources (tokenpull JSONL canon, ccusage CLI, token-dashboard SQLite, tokscale report), and the output shape (side-by-side with delta % vs tokenpull baseline). The added note that it also computes the cascade (Υ, SNR, Leverage, class) distinguishes it from both tokenpull and diagnose_cascade.

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?

It states the two concrete situations to use it: validating numbers before submitting and understanding discrepancies between tools, and adds a platform caveat ("Claude only for token-dash; codex and others use tokenpull + ccusage + tokscale"). It stops short of explicitly routing an agent to a named sibling for single-source or cascade-only needs.

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