Skip to main content
Glama
gbatistuta0

AppFactory

by gbatistuta0
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Orchestrator Needs Human

orchestrator_needs_human
Idempotent

Generates NEEDS_HUMAN.md when self-correction is exhausted, returning its path to stop the loop and let a human unblock the failing stage.

Instructions

Write NEEDS_HUMAN.md when self-correction is exhausted and return its path.

Use when: a stage keeps failing and only the human can unblock it (stop the loop afterwards). Returns: {ok, path}.

Input Schema

NameRequiredDescriptionDefault
stageYesPipeline stage id, e.g. 'aso', 'screenshots', 'features' (see pipeline_status for the list).
reasonYesWhy self-correction is exhausted (what failed).
app_dirYesAbsolute path to the app project directory (contains app.spec.json), e.g. /Users/me/Apps/MyApp.
how_to_resolveYesWhat the human needs to do to unblock the stage.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.5
    • addedInput schema / properties / app_dir / description
      Added value: +"Absolute path to the app project directory (contains app.spec.json), e.g. /Users/me/Apps/MyApp."
    • addedInput schema / properties / how_to_resolve / description
      Added value: +"What the human needs to do to unblock the stage."
    • addedInput schema / properties / reason / description
      Added value: +"Why self-correction is exhausted (what failed)."
    • addedInput schema / properties / stage / description
      Added value: +"Pipeline stage id, e.g. 'aso', 'screenshots', 'features' (see pipeline_status for the list)."
  2. First observedv0.1.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and idempotentHint=true, and the description adds the key behavioral fact that the loop should stop afterward. It doesn't fully explain side effects (does it also halt the orchestrator? does it overwrite existing NEEDS_HUMAN.md?), but it meaningfully exceeds the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight lines with front-loaded action, a use-when condition, and the return shape – no wasted words.

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?

Covers action, trigger, and return value with an output schema present. Minor gaps remain around whether writing is overwrite-safe and how it interacts with the orchestrator loop, but it is sufficient for correct invocation.

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 coverage is 100%, so all four required params are documented in the schema itself. The description adds no parameter detail beyond implying the file path output, so baseline 3 is appropriate.

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+resource ('Write NEEDS_HUMAN.md') and its trigger ('when self-correction is exhausted'), plus the return value. Clearly distinguishable from siblings like orchestrator_record_attempt or pipeline_mark.

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

Usage Guidelines5/5

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

Explicitly names the condition ('a stage keeps failing and only the human can unblock it') and adds a critical operational caveat ('stop the loop afterwards'), which is genuine when-to-use guidance.

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