Skip to main content
Glama
OrgMentem

zotio

by OrgMentem
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Hybrid

workflow_submit

Destructive

Submit an inline multi-step workflow executed by zotio's workflow runner — previews unless yes; one approval, one journal run id; steps apply in order and a failed step does not roll back earlier writes; steps validated per-command exactly…

Instructions

Submit an inline multi-step workflow executed by zotio's workflow runner — previews unless yes; one approval, one journal run id; steps apply in order and a failed step does not roll back earlier writes; steps validated per-command exactly like command_run.

Input Schema

NameRequiredDescriptionDefault
yesNoApply the full workflow once instead of previewing it.
varsNoWorkflow variable values.
stepsYesValidated workflow steps.
continue_on_errorNoContinue executing later steps after a step fails.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.29.0
    • addedInput schema / properties / steps / items / properties / stdin_select
      Added value: +{
+  "description": "JSON selector over the stdin_from step's output, such as findings[kind=missing_doi].item_key; each selected value becomes one stdin line. Missing, malformed, or incompatible selections fail the step; no values skip it.",
+  "type": "string"
+}
  2. Addedv0.9.1

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations (destructiveHint=true, idempotentHint=false) by disclosing the crucial partial-failure contract: 'a failed step does not roll back earlier writes'. It also discloses the preview-by-default gating ('unless yes'), the single-approval/single-journal-run model, and per-command validation parity with command_run — exactly the operational details an agent needs before a destructive batch call.

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?

A single front-loaded sentence where every clause carries distinct information (preview gate, approval/journal model, ordering, rollback semantics, validation parity). The em-dash chaining makes it dense but there is no filler to cut.

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 a deeply nested step schema, no output schema, and destructive annotations, the description covers the execution model, failure semantics, and the preview/apply gate, and even names the journal run id return handle. It is silent on how vars resolve into step args and on stdin_from/stdin_select interplay, which is the remaining gap.

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 yes, vars, steps, continue_on_error, and the nested step fields. The description only restates the yes/preview behavior ('previews unless yes') and adds no syntax, ordering, or var-resolution detail beyond the structured fields. Baseline 3 applies.

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 — 'Submit an inline multi-step workflow executed by zotio's workflow runner' — and explicitly positions it against the sibling command_run ('steps validated per-command exactly like command_run'). An agent can tell this is the batch/multi-step counterpart to command_run without opening a schema.

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?

The description gives a clear conditional: 'previews unless yes', plus 'one approval, one journal run id' to set expectations about the apply path. It implies but never explicitly says 'use this instead of issuing several command_run calls', so the alternative-selection guidance is inferred rather than stated.

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

Deploy Server

Other Tools