alma-corpus-mcp

beam_and_brightness

Convert between Jy/beam and brightness temperature (K) for a Gaussian beam, optionally using Planck inversion, and report beam areas for ALMA data.

Instructions

Convert between Jy/beam and brightness temperature (K) for a Gaussian beam, and report beam areas.

Rayleigh-Jeans: T = S c^2 / (2 k nu^2 Omega) = 1.222e6 S(Jy/beam) / (nu_GHz^2 bmaj bmin) with FWHMs in arcsec. planck=True uses the full Planck inversion T = (h nu / k) / ln(1 + 2 h nu^3 / (c^2 I_nu)) (no CMB term). direction: 'jy_to_k' (value in Jy/beam) or 'k_to_jy' (value in K). Limits: T_B equals the gas or dust temperature only for optically thick emission that fills the beam.

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": {
      "value": "<value>",
      "freq_ghz": "<freq_ghz>",
      "bmaj_arcsec": "<bmaj_arcsec>",
      "bmin_arcsec": "<bmin_arcsec>"
    },
    "name": "beam_and_brightness"
  }
}

Input Schema

Name	Required	Default
`value`	Yes
`planck`	No
`freq_ghz`	Yes
`direction`	No	jy_to_k
`bmaj_arcsec`	Yes
`bmin_arcsec`	Yes
`pixel_arcsec`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A4.2/5.0

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 so well: it states the exact Rayleigh-Jeans formula, the constant, the unit conventions (Jy/beam, GHz, arcsec), that planck=True omits the CMB term, and the physical assumption required for the result to be a temperature. The gap is that it never says what is actually returned (temperature only, or temperature plus beam area in sr/arcsec^2) even though 'report beam areas' implies a second output.

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 lead sentence states purpose first, then formulas, then option semantics, then limits – a sensible front-loaded order with no filler. The formula line is notation-dense, but for a scientific conversion tool that density buys precision rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter tool with no annotations and no output schema, the description covers the physics and inputs thoroughly but leaves two gaps an agent needs: the shape of the return value(s) and the role of pixel_arcsec. Those omissions keep it at minimum-viable-plus rather than complete.

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 description coverage is 0%, so the description must compensate, and it mostly does: it fixes units and meaning for value (Jy/beam or K depending on direction), freq_ghz (nu_GHz), bmaj_arcsec/bmin_arcsec (FWHMs in arcsec), and the two option flags. The exception is pixel_arcsec, which is never mentioned, leaving the agent to guess what it affects.

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 first sentence names a specific verb and resource: 'Convert between Jy/beam and brightness temperature (K) for a Gaussian beam, and report beam areas.' No sibling tool in the list performs unit conversion, so the agent can distinguish it at a glance from flux/mass/fit tools such as dust_mass_from_flux or fit_modified_blackbody.

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?

It gives concrete selection semantics for two optional parameters ('direction: jy_to_k ... or k_to_jy', 'planck=True uses the full Planck inversion') and a validity boundary ('T_B equals the gas or dust temperature only for optically thick emission'). What is missing is explicit routing against alternatives, e.g. when to just use the Rayleigh-Jeans approximation vs planck=True, or whether any sibling performs a related conversion.

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