Skip to main content
Glama
Smart Quota Orchestrator

Smart Quota Orchestrator

by ElNeMeR70

sqo_context_health

Measure quadratic Context-Rot risk in the active conversation and emit a compact Zero-Loss Handoff Snapshot to preserve context continuity.

Instructions

Measure quadratic session Context-Rot risk (0-100) on the active conversation transcript and emit a ready-to-paste <350-token Zero-Loss Handoff Snapshot.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "workspace": "<workspace>"
    },
    "name": "sqo_context_health"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNoCurrent engineering goal for the handoff snapshot.
workspaceYesWorkspace root directory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv13.0.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full burden. It discloses the two outputs (numeric risk and a bounded <350-token artifact) but says nothing about whether the call is read-only, whether a snapshot file is written or merely returned in the response, what permissions or workspace access are required, or the cost/latency profile of scanning a full transcript.

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?

A single front-loaded sentence that opens with the measurement action and closes with the produced artifact, with no filler. It is dense with proprietary jargon ("quadratic session Context-Rot") that an uninitiated agent may not parse, which keeps it just short of exemplary.

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?

With no output schema, the description must explain return values, and it does name the score range and the snapshot token budget. However, for a tool that appears to analyze an entire conversation and produce a handoff artifact, the description is silent on side effects, snapshot persistence, and how the score should be interpreted or acted upon.

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

Parameters3/5

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

Schema description coverage is 100% with only two parameters (workspace required, goal optional), and the schema already explains both. The description adds no additional meaning about how `goal` shapes the emitted snapshot or how `workspace` interacts with the "active conversation transcript" scope, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb pair ("Measure ... and emit") applied to specific resources: a 0-100 context-rot risk score on the active transcript and a <350-token handoff snapshot. The purpose is unambiguous, though it does not name or distinguish itself from plausible siblings such as sqo_context_pack, sqo_checkpoint, or sqo_compress_prompt, leaving the agent to infer the boundary from the domain vocabulary.

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

Usage Guidelines2/5

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

There is no explicit when-to-use, when-not-to-use, or alternative routing. The vocabulary ("Context-Rot risk", "Handoff Snapshot") hints at the scenario of a long conversation needing a handoff, but no trigger condition, prerequisite, or sibling exclusion is stated, so the agent must guess at selection.

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