Galaxy Cluster Catalogs MCP Server

fetch_cluster_selection_function

Download and save survey selection-function tables (completeness vs observable) for Planck, ACT, or SPT cluster catalogs, providing inputs to forward-model cluster counts.

Instructions

Fetch the survey selection function / completeness characterisation for a cluster survey.

Use to get the detection probability as a function of the survey observable
(Planck: completeness C(Y500, theta500); ACT: Q-filter + RMS noise per tile;
SPT: field areas + noise correction factors). These are the inputs needed to
forward-model cluster counts via predict_cluster_counts_lcdm.

Planck data: range-fetches only the ~120 KB tail of the 403 MB FITS file.
ACT data: streams the 7.4 GB tarball but extracts only the ~2 MB selFn tables.
SPT data: hard-coded field parameters from Bocquet+19 (no download needed).

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": "fetch_cluster_selection_function"
  }
}

Input Schema

Name	Required	Description	Default
`dataset`	No	Dataset key: psz2, act_dr6, or spt_sz.	psz2
`variant`	No	Planck variant: MMF3_cosmology (default, 65%% sky), union_survey (84%% sky). Ignored for ACT/SPT.
`output_dir`	Yes	Directory for selection-function CSV/JSON.

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

A4.6/5.0

Behavior5/5

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 so well: it discloses the network cost per dataset (range-fetch of the ~120 KB tail of a 403 MB FITS file; streaming a 7.4 GB tarball to extract ~2 MB; SPT needs no download at all). That is exactly the kind of cost/provenance information an agent needs before invoking a data-fetching tool.

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?

Three short paragraphs: purpose first, usage and downstream consumer second, per-dataset data-access facts third. Every sentence carries new information and the most decision-relevant content is front-loaded.

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?

For a network-backed fetcher with an output schema present, the description covers purpose, downstream use, and download cost per dataset, which is enough to call it correctly. Remaining gaps are minor: no mention of authentication, caching, or what happens if output_dir already contains files.

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, but the description adds meaning beyond the schema by mapping each dataset key (Planck/ACT/SPT) to a concrete data source, observable, and download behavior, which tells the agent the practical consequence of the dataset choice. It does not clarify the output_dir semantics (overwrite behavior, existing files), keeping it below 5.

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 ('Fetch the survey selection function / completeness characterisation for a cluster survey') and immediately pins down what the artifact contains per survey (Planck C(Y500, theta500), ACT Q-filter + RMS per tile, SPT field areas). This clearly separates it from siblings like fetch_cluster_catalog, which would return object lists rather than a detection-probability characterisation.

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?

Explicitly says when to use it ('Use to get the detection probability as a function of the survey observable') and names the downstream consumer, predict_cluster_counts_lcdm, which routes the agent correctly. It does not state any when-not condition (e.g. use fetch_cluster_catalog if you only need the cluster list), so it falls short of the full 5.

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