Mindjack

test_hypothesis

Read-only

Test cohort hypotheses with numeric filters to compare rug rate, peak-gain percentiles, time to peak, and collapse speed against the index base. Returns aggregates and a one-sentence finding.

Instructions

[$0.025] Measure what happened to every indexed launch matching your filters: rug rate against the index base rate, peak-gain percentiles, time to peak, collapse speed. Answers pattern questions like 'do launches with under 200 holders die faster?'; to shortlist live tokens to act on, use find_tokens instead. filters is {field: {min,max}} over numeric fields listed by get_coverage, e.g. {total_holders: {min: 200}}. Returns cohort aggregates and a one-sentence finding, never per-token rows. Read-only over stored history; measured past, not a forecast.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "filters": {
        "total_holders": {
          "min": 200
        }
      },
      "window_days": 30
    },
    "name": "test_hypothesis"
  }
}

Input Schema

Name	Required	Description	Default
`filters`	Yes	Field bounds as {min,max}; get_coverage lists the fields.
`window_days`	No	Cohort window, days. Default 30.

Output Schema

Name	Required	Description
`says`	No	The finding in one plain sentence, safe to quote.
`_meta`	No
`cohort`	No	n, rug_pct, base_rate_pct, rug_lift_vs_base, median_peak_gain_pct, p75/p90_peak_gain_pct,...
`filters`	No	The filters applied, echoed back.
`disclaimer`	No	Measured history, not a forecast, and not adjusted for slippage or fees.
`window_days`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.4.4Aug 22, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Read-only over stored history; measured past, not a forecast.' It further discloses return behavior ('Returns cohort aggregates and a one-sentence finding, never per-token rows') and the cost, adding meaningful context 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?

The description is compact yet information-dense, front-loading the core measurement purpose, then covering cost, alternatives, filter syntax, return shape, and safety. Every sentence earns its place with no filler or repetition of schema details.

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

Completeness5/5

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

Given the two-parameter schema, output schema presence, and annotations, the description covers everything needed to decide when and how to call the tool: purpose, filter format, field source, expected return shape, alternative tool, cost, and read-only semantics. Nothing critical is missing.

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 baseline is 3. The description adds real value by explaining the filters shape as '{field: {min,max}}', grounding it in fields from get_coverage, and giving a concrete example '{total_holders: {min: 200}}'. This goes beyond the schema's bare object type.

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 states a clear verb and resource: 'Measure what happened to every indexed launch matching your filters' and enumerates specific outputs (rug rate, peak-gain percentiles, time to peak, collapse speed). It also distinguishes itself from find_tokens, so an agent can tell them apart without opening schemas.

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

Usage Guidelines5/5

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

The description explicitly identifies when to use this tool ('Answers pattern questions like do launches with under 200 holders die faster?') and names the alternative for a different use case ('to shortlist live tokens to act on, use find_tokens instead'). It also clarifies that filters reference numeric fields listed by get_coverage, giving clear context for correct invocation.

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