Supernova Cosmology MCP Server

fetch_sn_sample

Download and tidy a Type Ia supernova Hubble diagram with its full statistical and systematic covariance, writing a CSV and matching covariance array for plotting or external analysis.

Instructions

Download (first use) and tidy one SN Ia Hubble diagram with its FULL stat+sys covariance.

Use this first: it writes `<dataset>_hd.csv` (cid, survey, z, zhel, mu, mu_err_diag,
is_calibrator) and `<dataset>_cov.npy` (the matching sub-covariance in mag^2, same row
order). Every other tool can take the dataset name directly, but the CSV is what you
hand to plotting or external codes. Union3 is a 22-node binned (compressed) Hubble
diagram - there is no public per-SN Union3 table.

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_sn_sample"
  }
}

Input Schema

Name	Required	Description	Default
`zmax`	No	Keep z_HD <= zmax.
`zmin`	No	Keep z_HD > zmin. None = release standard (Pantheon+ 0.01, others 0).
`dataset`	No	pantheonplus \| des5yr \| union3 \| des_dovekie (see list_sn_datasets).	pantheonplus
`output_dir`	Yes	Directory for the CSV + covariance .npy.
`calibrators`	No	Pantheon+ Cepheid-host calibrators (IS_CALIBRATOR=1): include \| exclude \| only. Other samples have none.	include

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

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well on side effects: it names the exact files written (`<dataset>_hd.csv`, `<dataset>_cov.npy`), lists the CSV columns, and states the covariance units and row-order alignment. Gaps remain on download/auth requirements, approximate size or runtime, and whether existing files in output_dir are overwritten.

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 sentence, then side effects, then cross-tool guidance. Slightly dense parenthetical column list, but every element is informative and nothing reads as filler.

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?

An output schema exists, yet the description correctly focuses on the on-disk artifacts and their relationship to downstream plotting/external codes, which is exactly what the schema cannot convey. For a five-parameter fetch tool with full schema coverage, no agent-critical information is missing.

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 zmax, zmin defaults, dataset enum, and calibrator modes; baseline 3 applies. The description adds only the Union3 caveat about dataset granularity, and otherwise does not extend parameter meaning beyond the schema.

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 ("Download ... and tidy one SN Ia Hubble diagram with its FULL stat+sys covariance") and distinguishes itself from siblings by noting that every other tool takes the dataset name directly. The parenthetical "(first use)" plus the Union3 note make the scope unambiguous.

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?

"Use this first" gives an explicit ordering rule, and "Every other tool can take the dataset name directly" explains why the agent does not need to re-invoke this for downstream steps. It also flags the Union3 exception (22-node binned compressed diagram, no per-SN public table) so the agent is not surprised by that dataset's granularity.

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