sima

Overview Schema Source Related Servers Discussions Admin

plot_variance_decomposition

Plot forecast-error variance decomposition as a panel figure showing how much each shock explains a variable's h-step forecast variance over time, with optional bootstrap confidence bands.

Instructions

FIGURE — The forecast-error variance decomposition, in the IRF's layout.

Panel (i, j): the % of the h-step forecast-error variance of i due to the shock of j, h = 1..H, as impulses on a 0-100 axis with the 95 % band dashed. A row reads the same as in plot_impulse_response. On a VEC: the levels' decomposition (drvec), the bootstrap's band from irf_bands.

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": {
      "name": "<name>"
    },
    "name": "plot_variance_decomposition"
  }
}

Input Schema

Name	Required	Description	Default
`name`	Yes
`path`	No
`bands`	No
`ndraws`	No
`horizon`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 30, 2026

TDQS

B3/5.0

Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose the visual contract (panel (i,j), 0-100 axis, dashed 95% band, h=1..H) and VEC-specific behavior (levels decomposition via drvec, bootstrap band from irf_bands). It omits whether a file is written and where, and that the band entails a bootstrap of ndraws replications — a meaningful cost/compute trait for a plotting tool.

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 'FIGURE —' lead front-loads the artifact, and the remaining sentences are dense with layout and band information rather than filler. Some VEC shorthand (drvec, irf_bands) is terse but not wasteful.

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?

For a 5-parameter plotting tool with no annotations and no output schema, the figure content and panel layout are well covered. Missing are the computation prerequisite, what path does, and how band inputs interact — gaps an agent must guess at before invoking.

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 coverage is 0% and none of the five parameters are named or explained. 'h = 1..H' and the '95 % band dashed' gesture at horizon and bands, but path, ndraws, and the required name are entirely unaddressed, so the description does not compensate for the coverage gap.

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 'FIGURE' and names the concrete artifact — the forecast-error variance decomposition — plus its panel semantics, so an agent knows this renders a plot rather than computing one. It never explicitly distinguishes itself from the sibling variance_decomposition (the computation) or plot_impulse_response, leaving the read-vs-compute split to inference.

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 statement of when to call this versus variance_decomposition, nor any prerequisite (e.g. that a decomposition must already exist). 'A row reads the same as in plot_impulse_response' is about interpreting output, not about tool selection.

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