Skip to main content
Glama

Check totals sweep

check_totals_sweep
Read-only

Computes finite-difference total derivatives at multiple step sizes, flags derivatives that change with step as numerical noise, and recommends a step before SLSQP.

Instructions

Finite-difference total derivatives at several step sizes, flagging derivatives that change with the step (numerical noise from black-box codes) and recommending a step. Run it before SLSQP.

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": {
      "problem_id": "<problem_id>",
      "of": "<of>",
      "wrt": "<wrt>"
    },
    "name": "check_totals_sweep"
  }
}

Input Schema

NameRequiredDescriptionDefault
ofYes
wrtYes
formNoforward
stepsNo
step_calcNoabs
problem_idYes
noise_rel_tolNo

Output Schema

NameRequiredDescriptionDefault
errorNo
entriesNo
messagesNo
any_noisyNo
captured_outputNo
recommended_stepNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true, so the safety profile is covered. The description adds genuine behavioral context: it sweeps multiple step sizes, detects derivatives that change with the step, attributes that to numerical noise in black-box codes, and produces a step recommendation. It does not discuss cost or failure behavior, but adds meaningful value beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly written sentences, with the core behavior and the key behavioral trait (step sensitivity) front-loaded. Nothing is redundant with the title or annotations.

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?

The output schema means return values need not be explained, and annotations cover the read-only nature. However, for a seven-parameter tool with zero schema descriptions, the definition leaves too many parameters unexplained to be fully complete, even though the purpose and workflow trigger are clear.

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

Parameters2/5

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

Schema description coverage is 0% across seven parameters, so the description must carry the burden and largely does not. It alludes to step sizes and implicitly to a noise tolerance, but never explains the required of/wrt/problem_id, the forward/central form choice, or abs-vs-rel step scaling.

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 names a specific computation (finite-difference total derivatives across several step sizes) plus two distinctive behaviors: flagging step-sensitive derivatives and recommending a step. This clearly separates it from the sibling compute_totals and from step-configuration tools.

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 gives an explicit trigger: "Run it before SLSQP." That tells an agent when this tool belongs in a workflow. It does not name the alternative (compute_totals) or state when not to use it, so it stops short of full routing guidance.

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