Skip to main content
Glama
Galaxy Cluster Catalogs MCP Server

Galaxy Cluster Catalogs MCP Server

export_dispatch_pack

Exports compute kernels and a manifest for clients to stage and submit HPC runs with their own credentials, keeping project tokens off this server.

Instructions

Hand THIS server's compute kernels to the client for HPC runs.

Returns the ``tools/`` package as in-band text files plus a manifest of
kernel entry points (dotted function path, args shape, node-side
pip_deps, walltime hint). The CLIENT - which holds the facility tokens,
Globus endpoint, project and workdir - stages and submits the kernels
with ITS OWN credentials (e.g. the hep-genesis facility servers'
run_pack_kernel tool). Nothing credential-shaped or project-shaped is
needed on, or returned by, this server.

Clients that recognise the ``dispatch_pack`` key should save the files
locally and NOT echo their contents into the conversation.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "export_dispatch_pack"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does well: it spells out the return shape (text files plus a manifest with dotted function path, args shape, pip_deps and walltime hint) and clarifies that nothing credential-shaped or project-shaped is needed or returned. It omits the read-only nature, payload size limits, and any rate or timeout behavior on a potentially large in-band file transfer.

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?

Three short paragraphs, front-loaded with the core action, then the return contents, then operational guidance. Every sentence adds information. Minor RST markup and the quoted key name are slightly noisy but not wasteful.

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?

With no output schema and no annotations, the description must explain both the returned payload and the integration contract, and it covers both: the file set, the manifest fields, and the client's responsibility for staging and submission. It is missing only operational bounds such as file size or truncation, which matter for an in-band transfer.

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?

The tool takes zero parameters, which is the baseline 4 case. The description correctly implies no inputs are required by explaining that credentials, project and workdir live entirely on the client side.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a concrete verb and resource: it hands this server's compute kernels to the client, returning the tools/ package as in-band text files plus a manifest. That is far more specific than a restated name. It stops short of a 5 because it never explicitly contrasts itself with the similarly named siblings get_dispatch and set_dispatch, leaving the agent to infer the difference.

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 states the context of use, HPC runs where the client holds the facility tokens and Globus endpoint, and points at an example consumer (run_pack_kernel). It also gives a handling instruction: save the files locally and do not echo their contents. It does not state a when-not or explicitly name sibling alternatives, so it falls short of a 5.

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