Galaxy Cluster Catalogs MCP Server

compare_mass_calibration

Quantify relative mass bias between galaxy-cluster surveys from matched catalogs by reporting median mass ratios, log-normal scatter, redshift trends, and optional slope fits.

Instructions

Mass-calibration comparison for matched clusters: M500_b vs M500_a scatter, ratio vs z and vs mass.

Use after crossmatch_catalogs to quantify relative mass bias between surveys
(e.g. Planck's hydrostatic 1-b ~0.8 vs WL-calibrated SPT/ACT, or SZ vs eROSITA).
Reports median ratio with bootstrap error, log-normal scatter, per-z-bin ratios
and (optionally) a power-law slope.

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": {
      "output_dir": "<output_dir>",
      "matched_csv": "<matched_csv>"
    },
    "name": "compare_mass_calibration"
  }
}

Input Schema

Name	Required	Description
`z_edges`	No	Redshift bins for the ratio trend (default 0,0.2,0.4,0.6,0.8,1.2).
`fit_slope`	No	Fit ln M_b = alpha + beta ln(M_a/3e14) by orthogonal-ish (BCES-Y\|X and bisector) regression.
`output_dir`	Yes	Directory for the PNG / CSV.
`matched_csv`	Yes	CSV written by crossmatch_catalogs.

Output Schema

Name	Required	Description	Default
`files`	Yes
`status`	Yes
`message`	Yes
`metadata`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations at all, the description carries the full burden and does substantial work: it discloses the statistics computed (median ratio with bootstrap error, log-normal scatter, per-z-bin ratios, optional power-law slope) so the agent knows the computation is nontrivial and file-producing. It omits practical behavior such as how sparse z-bins or insufficient pairs are handled, and does not state that artifacts are written into output_dir (that only appears in the parameter schema).

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?

Four short sentences, front-loaded with what the tool produces, then prerequisite ordering, then outputs. No filler, though the parenthetical survey examples are illustrative rather than operational and could be trimmed.

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?

An output schema exists and the schema fully documents all four parameters, so the description need not explain return values. It covers purpose, prerequisite and computed quantities; the only real gap is handling of edge cases (too few clusters per z bin, existing output directory contents) for what is a multi-stage analysis tool.

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% and z_edges/fit_slope/output_dir/matched_csv each carry their own description including defaults and the regression method. The prose only restates that z bins drive the ratio trend and the slope is optional, adding little beyond the schema, so the baseline 3 applies.

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?

Uses a specific verb and resource ('Mass-calibration comparison for matched clusters') and enumerates exactly what is produced: M500_b vs M500_a scatter, ratio vs z, ratio vs mass. The scope is narrow enough that an agent can distinguish it from siblings like plot_mass_redshift or plot_counts_vs_prediction without opening a schema.

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?

'Use after crossmatch_catalogs' establishes the pipeline prerequisite and implicitly names the producing sibling, and the stated scientific purpose (quantify relative mass bias between surveys, with Planck 1-b~0.8 vs SPT/ACT examples) tells the agent the scenario it serves. It stops short of saying when NOT to use it or what to do if no matched CSV exists.

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