Skip to main content
Glama

jean — Molecular Biology & Genomics

run_workflow

Run a workflow graph: nodes naming tools, wires carrying one node’s output into another’s input, $whenExpression to make a step conditional, and scatter to run a step once per element of a list. Returns the run record — per-node status, outputs and errors, in topological order.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
graphYesA workflow graph: nodes naming tools, wires carrying one node’s output into another’s input, and the two constructs a single tool call cannot express — `$whenExpression` (run this node only if…) and `scatter` (run it once per element of a list input, gathering every output into an array).
_filesNoThe project's files, standing in for the project open in the editor: each is one record reference (a `file`, `sample`, `accession` or named `sequence`). Every sequence record they hold becomes a library document a tool can name in its `sequences`/`parts`/`document` arguments (a multi-record file as `file · record`), and a tool reading a file by name (a trace, an alignment) finds it here.
_subjectNoThe record this call acts on, standing in for the document open in the editor. Exactly one of: `sequence`, `file`, `sample`, `accession`. This server holds no project, so a tool needing a subject gets it here or refuses by name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false and openWorldHint=true, so the mutating/open nature is already covered. The description adds genuine value by saying the run record contains per-node status, outputs and errors in topological order, implying partial results and collected errors rather than an abort-on-first-failure, but it says nothing about side effects, idempotency, or failure/abort semantics.

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?

Two dense sentences, front-loaded with the action and then the return shape; every clause carries information. It is slightly overloaded with construct names that the schema repeats, but there is no filler.

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?

For a tool with no output schema, the description does describe the return record's contents and ordering. Combined with annotations covering the non-read-only, open-world profile and a fully documented schema, little is missing beyond error/abort behavior and guidance against sibling tools.

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 baseline is 3; the nested graph/edges/nodes properties already document $whenExpression, scatter and wiring in detail. The description restates those constructs without adding syntax or constraints the schema lacks.

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?

States a specific verb and resource ('run a workflow graph') and elaborates the graph's semantics (nodes naming tools, wires, $whenExpression, scatter), so an agent knows exactly what is executed. It does not differentiate from the closely related siblings validate_workflow and list_workflow_templates, which keeps it below a 5.

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

Usage Guidelines2/5

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

No explicit when-to-use or when-not-to-use guidance. With siblings named validate_workflow and list_workflow_templates in the same server, the description should say when to validate or list instead of run, and it offers nothing.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources