ShapelessAI

Start a job

jobs_create

Start a durable job from a goal, optionally with files attached. The run keeps going server-side; returns the job id and its web url to poll or continue. Needs the write scope.

Input Schema

TableJSON Schema

Name	Required	Description
`goal`	Yes	What to do, up to 4000 characters.
`label`	No	Job title, up to 80 characters. Defaults to the goal's first line.
`model`	No	Brain for this run: claude-opus-5-5, claude-opus-5, claude-sonnet-5, claude-fable-5-1, gpt-5.6-sol or gpt-6-astra. Absent means the account's default. A model test runs the same goal once per model.
`autoRun`	No	Execute the plan the moment it is ready instead of pausing for approval. Deliverables still land as proposed drafts.
`timezone`	No	IANA timezone for scheduling language in the goal.
`budgetUsd`	No	Budget for the run, in dollars.
`mediaKeys`	No	Media keys already in the account (from assets_upload or assets_list) to attach.
`characters`	No	Actors to star in this job, by slug or id (characters_list). The agent always sees the whole roster; these are the ones it must use.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes
`url`	Yes
`title`	Yes
`status`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 7, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "id": {
+      "type": "string"
+    },
+    "status": {
+      "type": "string"
+    },
+    "title": {
+      "type": "string"
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "id",
+    "title",
+    "status",
+    "url"
+  ],
+  "type": "object"
+}

First observedSep 29, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so safety is partly covered. The description still adds real value: the run persists server-side after the call returns, it yields a job id and web url for polling, and it requires the write scope. It does not mention rate limits, budget enforcement, or what happens when the run fails.

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 sentences with zero waste. The core action is front-loaded, the persistence behavior follows, and the scope requirement closes it out.

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?

An output schema exists, so return values need not be spelled out, and annotations cover the safety profile. The description supplies the async persistence model and auth scope, leaving only minor gaps around failure behavior and cost/budget semantics.

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 description only adds that files may be attached, which loosely maps to mediaKeys; it says nothing about goal, model, autoRun, budgetUsd, or characters beyond what the schema already explains in detail.

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 ("Start a durable job from a goal") plus the optional attachment capability, which is enough to identify the operation. It hints at the async lifecycle ("the run keeps going server-side") but never names the sibling tools that consume the returned job id (jobs_get, jobs_continue, jobs_run), so it stops short of full sibling differentiation.

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

Usage Guidelines3/5

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

"Needs the write scope" gives a clear prerequisite, and the durable/server-side framing implies this is the async entry point. But there is no explicit when-to-use versus jobs_run, jobs_continue, or jobs_brief, and no when-not-to-use guidance for an 8-parameter tool with a rich sibling set.

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

All ShapelessAI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.