Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

synthplot

Read-only

Plot any Synthetic Control variant—trajectory, gap, placebo, weights, conformal intervals—to inspect causal effects and diagnose fit.

Instructions

Unified plot function for all Synthetic Control variants.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`ax`	No	Pre-existing axes for single-panel plots.
`type`	No	Plot type: * ``'trajectory'`` -- treated vs synthetic over time. * ``'gap'`` -- effect (gap) over time. * ``'both'`` -- two-panel: trajectory + gap. * ``'weights'`` -- donor weight bar chart. * ``'placebo'`` -- placebo ATT distribution. * ``'placebo_gap'`` -- placebo gap spaghetti plot (Abadie et al. 2010). * ``'rmspe'`` -- post/pre RMSPE ratio histogram (Abadie et al. 2010). * ``'conformal'`` -- period-level effects + conformal CIs. * ``'staggered'`` -- cohort-level ATT comparison. * ``'factors'`` -- latent factor loadings (gsynth only). * ``'compare'`` -- overlay multiple results.	trajectory
`title`	No	Override the auto-generated title.
`top_n`	No	Number of donors to show in weight plots.
`detail`	No	Payload depth: 'minimal' (~150 tokens) for sub-step calls where only the point estimate is needed; 'standard' (~1K tokens) for diagnostics + coefficient table; 'agent' (~2K tokens, default) adds violations / next_steps / suggested_functions so the LLM can plan its next call without another round-trip.	agent
`labels`	No	Labels for ``type='compare'``.
`result`	Yes	Output of any ``synth()`` variant. Pass a list for ``type='compare'``.
`figsize`	No	Figure size. Auto-selected if None.
`as_handle`	No	If true, cache the fitted result on the server and return result_id + result_uri alongside the JSON payload so a subsequent tools/call can chain without re-running.
`data_path`	No	Absolute path or URL to a data file. Supported: .csv / .tsv / .txt (delimited), .parquet / .pq, .feather / .arrow, .xlsx / .xls, .dta (Stata), .json / .jsonl. Schemes: file://, s3://, gs://, https://.
`result_id`	No	Optional handle to a previously-fitted result (returned by an earlier call when as_handle=true). Tools that operate on a fitted object accept this in place of re-supplying data_path + columns.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

C2.9/5.0

Behavior2/5

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

The readOnlyHint annotation already indicates a non-mutating operation, and the description does not contradict this. However, it adds no behavioral context beyond the annotation—no mention of results caching, output formats, or side effects. With the annotation covering the safety profile, the description contributes little extra transparency.

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 description is a single short sentence, which is concise and front-loads the core purpose. However, it is so minimal that it omits any references to the supported plot types or usage scenarios, which slightly reduces its helpfulness despite the brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (13 parameters, multiple plot types, many sibling tools), the description is far too sparse. It does not explain what plot types are available, when to use this tool versus dedicated alternatives, or how results are handled (e.g., caching via as_handle). The schema covers parameter details, but the high-level context needed for correct selection is missing.

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%, so all 13 parameters are documented in the schema. The description adds no additional semantic nuance beyond what the schema already provides. This matches the baseline of 3 for high coverage.

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 clearly states the tool is a unified plot function for Synthetic Control variants, which distinguishes it from specialized plot tools like synth_compare or synth_sensitivity_plot. It names the resource (Synthetic Control variants) and the action (plot), though it could be more specific about what kinds of plots it produces.

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?

The description provides no guidance on when to use this tool versus the many dedicated plotting siblings (e.g., synth_compare, synth_sensitivity_plot, synthdid_plot). It simply claims to be 'unified' without explicitly stating that it is the default choice or that specific alternatives exist for particular plot types. An agent would have to infer usage from the schema.

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

Deploy Server