Galaxy Cluster Catalogs MCP Server

plot_counts_vs_prediction

Compare observed galaxy-cluster N(z) with LCDM predictions by plotting Poisson errors, residuals, and sigma8 profiles from prediction JSON files.

Instructions

Plot observed cluster N(z) (Poisson errors) against LCDM predictions, with a residual panel and the sigma8 profile if scanned.

Use after predict_cluster_counts_lcdm.

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>",
      "prediction_json": "<prediction_json>"
    },
    "name": "plot_counts_vs_prediction"
  }
}

Input Schema

Name	Required	Description	Default
`stem`	No	Output file stem.	counts_vs_lcdm
`output_dir`	Yes	Directory for the PNG.
`per_unit_z`	No	Plot dN/dz instead of N per bin.
`prediction_json`	Yes	One or more JSON files written by predict_cluster_counts_lcdm (e.g. different sigma8 or surveys).

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

A3.8/5.0

Behavior3/5

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

With no annotations at all, the description carries the full behavioral burden and it partially discharges it: it discloses that errors are Poisson, that a residual panel is drawn, and that a sigma8 profile appears only 'if scanned'. It omits that the tool writes a PNG to disk, what overwrite behavior to expect, and where the 'observed' counts come from (no parameter supplies them), which are the operationally important behaviors for a file-producing 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?

Two short sentences with zero filler, front-loaded with the primary output and followed by the precondition. Nothing needs trimming and nothing important is buried.

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?

The return value is covered by an output schema and the visual content is described, so the picture of the result is clear. The notable gap is that the observed-counts source is never stated even though no input parameter supplies it, which an agent needs to know before calling.

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 parameters are already documented and the baseline is 3. The description adds little beyond the schema — it says 'N(z)' without clarifying that the per_unit_z parameter toggles between dN/dz and counts per bin, and it does not explain how multiple prediction_json files are rendered in one figure.

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 names a specific verb and resource ('Plot observed cluster N(z)') plus the comparison target ('against LCDM predictions') and the extra panels included. It is clearly distinct from siblings such as plot_mass_redshift, plot_cluster_sky_map, and plot_completeness, so an agent can select it without opening the schema.

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

Usage Guidelines3/5

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

The sentence 'Use after predict_cluster_counts_lcdm' gives a sequencing constraint, which is genuinely useful. However, it does not say when to prefer this over other plotting siblings, nor what happens if no prediction exists yet — usage is implied rather than explicitly bounded.

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