Supernova Cosmology MCP Server

set_dispatch

Configure where this server's heavy cosmology tools execute (local, Polaris, or Perlmutter) and optionally set the artifact fetch directory; light tasks remain local.

Instructions

Set where THIS server's heavy tools execute: 'local' (this machine), 'polaris' (ALCF) or 'perlmutter' (NERSC).

Affects only this server's heavy (dispatchable) tools - never other
servers' dispatch state. Remote sites run each heavy call as one facility
job (staging + queue + walltime: minutes, not seconds) and need facility
sign-in - check with auth_status first. Light tools (listing, plotting,
small reads) always run locally. Optional artifact_dir sets where
produced files are fetched back to. Returns the active configuration.

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": {
      "site": "<site>"
    },
    "name": "set_dispatch"
  }
}

Input Schema

Name	Required	Description	Default
`site`	Yes
`artifact_dir`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A4.7/5.0

Behavior5/5

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: it discloses that remote calls become facility jobs with staging/queue/walltime latency in minutes, that facility sign-in is required, that only this server's tools are affected, and that produced files are fetched back to artifact_dir.

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?

Front-loaded with the core action and values, and each subsequent sentence adds operational detail that answers a predictable follow-up question. Slightly dense in the parenthetical about staging/queue/walltime, but nothing is 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?

For a 2-parameter configuration tool with an output schema, everything an agent needs is present: valid values, scope of effect, prerequisites, latency expectations, and artifact handling. Return values are covered by the output schema plus the closing sentence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% with no enums, so the description must supply the semantics, and it does: it names the three valid site values and explains artifact_dir as the destination for fetched-back produced files.

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 (set) and resource (this server's dispatch target), enumerates the three accepted sites, and scopes the effect to THIS server, which distinguishes it from get_dispatch and from any global dispatch state.

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 clear when-to-use context (heavy/dispatchable tools only, light tools always local) and a prerequisite ('check with auth_status first'). It does not explicitly point to get_dispatch for reading current state, though 'Returns the active configuration' partially covers that need.

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