Skip to main content
Glama

Create an AI task (draft)

create_task

Create a labeling or evaluation task as a draft; nobody is notified until publish_task. Typical order: list_pools, create_task with instructions, classes, rate, pool_ids and one example image per class, add_items, then publish_task after the user confirms.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rateNoHourly pay for the expert in EUR
typeNoDefault data_labeling
titleYes
domainNo
classesNoClass names experts choose from
deadlineNo
examplesNoExample images by public URL with the class they show. Labeling tasks need one per class before they can open.
languageNoLanguage of the instructions
pool_idsNoPools the task runs on (see list_pools)
expertiseNoWhat experts need to know, one line
allow_noteNo
annotationNoDefault classification
instructionsNoInstructions for the experts in Markdown. A table whose first column names the classes becomes the per-class briefing.
members_onlyNoOnly members of these pools see the task, even on public pools
multi_selectNo
qualificationNo
allow_cant_tellNoLet experts skip an item without a class (default true)
seconds_per_itemNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it delivers the single most important behavioral fact: the task is a draft and nobody is notified until publish_task. It also discloses the labeling prerequisite (one example image per class before a task can open). Gaps remain on permissions/ownership and error behavior, so it stops short of 5.

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?

Two sentences, front-loaded with the draft/no-notification fact and then the call sequence. Dense with actionable detail and 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 an 18-parameter mutation tool with no annotations and no output schema, the description covers the essential setup sequence and the draft semantics that an agent must know. It doesn't touch several consequential parameters (qualification, members_only, deadline), which is a real but minor gap given the schema documents them.

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 61%, so a moderate baseline applies. The description names instructions, classes, rate, pool_ids and examples and adds the 'one example image per class' constraint for examples plus a pointer to list_pools for pool_ids, but the other documented parameters (qualification, deadline, annotation, language, etc.) get no added meaning.

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 (create) and resource (labeling/evaluation task), and pins the scope with 'as a draft.' The parenthetical distinction from publish_task and update_task is clear enough that an agent can route without opening a sibling schema.

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?

Gives the explicit workflow order: list_pools, create_task, add_items, publish_task after user confirmation. This names the alternatives to reach for and the condition ('after the user confirms') that gates the follow-up call.

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