ABS · AI Business System

Make a plan

create_plan

Turn one sentence into an execution plan from the ABS knowledge base: phases, steps, schedule, forms and sources, plus what the knowledge base does not cover. Returns the plan code at once with status generating; building takes a minute or two, so call get_plan with that code about every 20 seconds until status is draft. Saved as a draft the user reviews and submits in ABS. Uses the account's credits.

Input Schema

Name	Required	Description
`lang`	No	Answer language: zh (Chinese) or en (English)
`question`	Yes	What to achieve, in one sentence, e.g. 'Run a kaizen week to raise first-pass yield'
`start_date`	No	Start date, YYYY-MM-DD (default: from the request, or the next working start)

Output Schema

Name	Required	Description
`url`	Yes	Where the user reviews and submits it in ABS
`code`	Yes	Plan code, e.g. DRF-20261015-0001
`error`	No	Why it failed, when status is aborted
`status`	Yes	generating while ABS is still building it (check again with get_plan), draft when ready, aborted or stalled when it failed, submitted once the user submits it in ABS
`markdown`	No	The plan in Markdown: phases, steps, schedule, forms, sources, coverage and gaps
`progress`	No	Stages done so far, while generating
`question`	Yes	The request the plan was made from
`no_flow_reason`	No	Why no ready-made flow fitted, when that happened

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 15, 2026

addedOutput schema / properties / error

Added value: +{
+  "description": "Why it failed, when status is aborted",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / progress

Added value: +{
+  "description": "Stages done so far, while generating",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

changedOutput schema / properties / status / description

Previous value: -"draft until the user submits it in ABS"New value: +"generating while ABS is still building it (check again with get_plan), draft when ready, aborted or stalled when it failed, submitted once the user submits it in ABS"

First observedOct 15, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description adds genuinely new behavior: immediate return with status 'generating', an asynchronous build taking a minute or two, a specific polling interval, and the fact that the output lands as a user-reviewed draft rather than a finished artifact.

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?

Front-loaded with what the tool produces, then the async/polling mechanics, then the side effects (draft state, credit consumption). Sentences are dense and every one carries new information; nothing is restated from the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an async, credit-consuming generation tool, the description covers what an agent needs to act: it returns a code immediately, how long to wait, the polling target and cadence, the terminal status, and that a human submits the result. With an output schema present, it correctly avoids explaining return field shapes.

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 lang, question and start_date are already documented with format, enum and length constraints. The description reinforces that the input should be a single sentence but adds no syntax or constraint detail beyond the schema, so the baseline of 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?

The description opens with a specific verb+resource ('Turn one sentence into an execution plan') and enumerates the plan contents (phases, steps, schedule, forms, sources, coverage gaps), so the agent knows exactly what it produces. It also implicitly separates itself from get_plan by casting that sibling as the polling companion, which is the closest thing to a same-resource sibling.

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?

Usage is well spelled out: call this once, then poll get_plan roughly every 20 seconds until status is draft, and the result is a draft the user submits in ABS. It does not say when to prefer this over other planning-adjacent siblings like ask or diagnose, so it falls short of the explicit when/when-not/alternatives bar.

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

All ABS · AI Business System 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.