Galaxy Cluster Catalogs MCP Server

predict_cluster_counts_lcdm

Predicts LCDM cluster counts dN/dz above a mass threshold and compares them with a catalogue to test consistency and constrain sigma8.

Instructions

Predict LCDM cluster counts dN/dz above a mass threshold (Tinker+08 HMF x Eisenstein-Hu P(k)) and compare with a catalogue.

Use to ask "is this survey's N(z) above M consistent with LCDM / which sigma8?".
No selection function, mass scatter or Eddington bias is modelled: pick a
threshold where the catalogue is ~complete (SPT-SZ ~5e14 at z>0.25, ACT DR6
SNR>5 ~5e14, PSZ2 ~6e14 at z~0.2) and treat ratios at the 10-20% level as the
systematics floor (the mass-calibration uncertainty dominates). Heavy:
runs as an HPC kernel when dispatch is active.

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>"
    },
    "name": "predict_cluster_counts_lcdm"
  }
}

Input Schema

Name	Required	Description	Default
`h`	No	H0/100.
`ns`	No	Scalar spectral index.
`Ob0`	No	Baryon density today.
`Om0`	No	Matter density today.
`sigma8`	No	sigma8 today.
`z_edges`	No	Redshift bin edges (default 0.1..1.3 step 0.1).
`m500_min`	No	M500c threshold in 1e14 Msun (catalogue h70 units).
`mass_def`	No	Mass definition of the threshold.	500c
`area_deg2`	No	Survey area [deg^2]; default = the observed catalogue's registry area.
`output_dir`	Yes	Directory for the prediction CSV/JSON.
`sigma8_scan`	No	Optional sigma8 grid for a Poisson -2lnL profile vs the observed counts (each point ~1-3 s locally).
`observed_catalog`	No	Harmonised CSV or dataset key: its N(z, M500 >= m500_min) is compared with the prediction.

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

A4.2/5.0

Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses model omissions (no selection function, mass scatter or Eddington bias), the dominant systematic, and that it runs as an HPC kernel when dispatch is active. The runtime statement is slightly ambiguous about what happens when dispatch is not active, which is the main gap.

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 purpose is front-loaded in the first clause, followed by usage framing and then caveats in roughly priority order. It is dense but nearly every sentence carries information; the line-broken layout is slightly awkward but not wasteful.

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?

For a 12-parameter physics computation with an output schema and no annotations, the description supplies the model, the intended inference, the systematic limitations, and performance expectations. An agent has enough to decide whether to call it and how to interpret the result ratios.

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 the schema already documents every parameter including units, defaults and bounds. The description reinforces threshold choice conceptually but adds no parameter-level detail (units, formats, interactions) beyond what the schema states, 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?

States a specific verb and resource (predict LCDM cluster counts dN/dz above a mass threshold) and names the exact model chain (Tinker+08 HMF x Eisenstein-Hu P(k)) plus the comparison against a catalogue. This clearly distinguishes it from the sibling compute_cluster_counts, which measures rather than predicts.

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?

Gives an explicit when-to-use framing ('is this survey's N(z) above M consistent with LCDM / which sigma8?') and concrete threshold guidance per survey (SPT-SZ, ACT DR6, PSZ2) with a 10-20% systematics floor. It does not name an alternative sibling tool or state when not to use it, which keeps it 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.