Skip to main content
Glama

Stored scenarios

scenario
Destructive

Save, validate, retrieve, and reverse-search stored macroeconomic stress cases; find the worst portfolio loss under a price or the lowest price reaching a loss level.

Instructions

Stored scenarios. Actions: list, get, save, validate, reverse.

Read guide(name="scenario-from-corpus") before building one. save checks the contract and writes scenarios/<id>.json; validate loads the macro and satellite versions the file names and names every problem that keeps the scenario from being computed, including corpus fragments not visible on the calculation day when the index exists, and reports how the elements are marked and what the scenario leaves unsaid under labels and warnings. reverse searches the scenario's family on portfolio: the worst loss under the price kappa, or the lowest price whose loss reaches level. bench returns the text of the bench event and starts its journal of corpus calls; build the scenario by the guide, then bench_save checks spec and keeps it with the journal and notes in the bench results, beside an empty review the expert fills. A bench scenario is never approved and never computed.

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": {
      "action": "<action>"
    },
    "name": "scenario"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoThe scenario id, which is also the name of its file: lowercase letters, digits and dashes.
seedNoThe seed of the reverse search: the same inputs give the same answer.
specNoThe scenario specification save checks against the contract before it writes the file.
drawsNoHow many paths the reverse search draws on every point of the family.
eventNoThe bench event bench and bench_save work on, like E017.
kappaNoThe price the reverse search fixes, for the worst loss under it.
levelNoThe loss level the reverse search finds the lowest price for.
notesNoWhat bench_save adds to the journal of the event: how the numbers of the scenario were chosen.
actionYesWhat to do: list, get, save, validate or reverse. save overwrites a scenario stored under the same id. bench starts the scenario of a bench event, bench_save keeps it in the bench results.
portfolioNoThe portfolio whose losses the reverse search measures.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.1.0
    • changedInput schema / properties / action / description
      Previous value: -"What to do: list, get, save, validate or reverse. save overwrites a scenario stored under the same id."New value: +"What to do: list, get, save, validate or reverse. save overwrites a scenario stored under the same id. bench starts the scenario of a bench event, bench_save keeps it in the bench results."
    • addedInput schema / properties / event
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "The bench event bench and bench_save work on, like E017."
      +}
    • addedInput schema / properties / notes
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "What bench_save adds to the journal of the event: how the numbers of the scenario were chosen."
      +}
  2. Changed8 schema fields changedv1.0.2
    • addedInput schema / properties / action / description
      Added value: +"What to do: list, get, save, validate or reverse. save overwrites a scenario stored under the same id."
    • addedInput schema / properties / draws / description
      Added value: +"How many paths the reverse search draws on every point of the family."
    • addedInput schema / properties / id / description
      Added value: +"The scenario id, which is also the name of its file: lowercase letters, digits and dashes."
    • addedInput schema / properties / kappa / description
      Added value: +"The price the reverse search fixes, for the worst loss under it."
    • addedInput schema / properties / level / description
      Added value: +"The loss level the reverse search finds the lowest price for."
    • addedInput schema / properties / portfolio / description
      Added value: +"The portfolio whose losses the reverse search measures."
    • addedInput schema / properties / seed / description
      Added value: +"The seed of the reverse search: the same inputs give the same answer."
    • addedInput schema / properties / spec / description
      Added value: +"The scenario specification save checks against the contract before it writes the file."
  3. Changed5 schema fields changedv1.0.1
    • addedInput schema / properties / draws
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
    • addedInput schema / properties / kappa
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
    • addedInput schema / properties / level
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
    • addedInput schema / properties / portfolio
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
    • addedInput schema / properties / seed
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
  4. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false; the description usefully reinforces this by stating `save` overwrites a scenario stored under the same id, and adds domain behavior such as 'a bench scenario is never approved and never computed' and that bench starts a journal of corpus calls. What it does not add is any permission/auth requirement, error behavior, or what happens on a failed contract check beyond 'names every problem'. Given annotations carry the safety profile, this is solid but not rich.

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

Conciseness3/5

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

The action list is correctly front-loaded, but the middle sentences are overloaded and hard to parse, especially the validate sentence that stacks 'loads the macro and satellite versions the file names and names every problem... including corpus fragments not visible on the calculation day'. Information is dense and useful but could be split into shorter, scannable statements.

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?

For a 10-parameter, multi-action tool this covers most of what an agent needs: the action set, the guide prerequisite, the overwrite semantics, and the bench workflow, and an output schema exists so return values need not be described. The remaining gap is the mismatch between the enumerated actions and the full set accepted by `action`, which could mislead an agent into missing `bench`/`bench_save`.

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%, so the schema already defines all ten parameters, making 3 the baseline. The description nonetheless adds real meaning beyond the schema by explaining the reverse-search pair semantically (the worst loss under price `kappa` vs the lowest price whose loss reaches `level`) and tying `notes` and `event` to the bench workflow.

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?

The description opens with the resource (stored scenarios) and enumerates concrete operations: list, get, save, validate, reverse, plus bench/bench_save. It distinguishes itself from siblings by naming `guide`, `portfolio`, and `bench_save` as separate surfaces. The only weakness is that the opening action list is incomplete relative to the action parameter, which also accepts `bench` and `bench_save`.

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 explicit sequencing guidance: read `guide(name="scenario-from-corpus")` before building one, build by the guide, then call `bench_save`. It also frames what validate and reverse are for. It stops short of saying when NOT to use this tool or which sibling to prefer for a given task, so it falls short of a 5.

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