Skip to main content
Glama

atlas_plan

Idempotent

Create a new open Work Order in local docs with linked spec section, implementing files, and checklist steps to structure feature plans before coding.

Instructions

Create a new ⬜ OPEN Work Order in local documentation, automatically linking the matching spec section (atlas_where), implements: files, and - [ ] checklist steps.

Use this tool when planning a new feature or breaking a user request into structured steps before coding.
Unlike `atlas_publish` (which records a finished result), `atlas_plan` assigns the next free Work Order
number, looks up the relevant spec anchor via BM25 search, and writes a checkable `- [ ]` step list.

Behavior & Output:
- Queries the documentation index for `topic`, attaches `Spec <anchor> (<path>:<line>)` and any `implements:` files.
- Writes `Work Order <N> — ⬜ OPEN (<topic>): ...` plus `- [ ] <step>` lines into `docs/ARCHITECTURE.md`.
- Pre-records `verify_symbols` in `.atlas/wo-symbols.yml` when provided.
- Returns JSON `{written, verified, wo, title, spec_anchor, spec_origin, implements, steps, line}`.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "topic": "<topic>"
    },
    "name": "atlas_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
woNoOptional explicit Work Order number. Omit or pass null to automatically assign the next free Work Order number.
stepsNoOptional list of concrete implementation steps to record as `- [ ]` checkboxes under the Work Order (e.g. ['Apply burn stacks in effects.py', 'Call tick_effects at end of turn', 'Add unit test']). All steps must be checked off via `atlas_set_status(task=..., status='done')` before the Work Order can be marked done.
topicYesTitle or topic of the Work Order to create (e.g. 'Damage Over Time' or 'Dialogue conditions'). Automatically searched against the documentation index (`atlas_where`) to link the matching spec anchor and `implements:` files.
verify_symbolsNoOptional list of target function or class names expected from this Work Order (pre-registered in `.atlas/wo-symbols.yml` so the wiring gate enforces them on completion).

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.4

TDQS

A4.4/5.0
Behavior4/5

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

With annotations already declaring readOnly=false and destructive=false, the description still adds real substance: which file is written (`docs/ARCHITECTURE.md`), that BM25 search attaches the spec anchor, and that `.atlas/wo-symbols.yml` is pre-populated. One tension is left unresolved: annotations claim idempotentHint=true while auto-assignment of 'the next free Work Order number' implies repeated calls with no `wo` produce distinct work orders.

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?

Front-loaded with the action, then a usage sentence, then a labeled 'Behavior & Output' block — easy to scan. The closing bullet restating the JSON return shape duplicates the output schema and is the one part that doesn't earn its place.

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?

Given an output schema exists, the description need not explain return values, yet it still names every side effect (docs file, symbols file) and the required follow-up workflow. For a four-parameter creation tool with annotations present, nothing an agent needs to call it correctly is missing.

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 the schema already documents all four parameters; the description mainly restates `topic` and `verify_symbols` behavior. It does add cross-tool meaning the schema only hints at (steps must be closed via `atlas_set_status` before completion, verify_symbols is enforced by the wiring gate), which lifts it slightly, but most of the semantic load is carried by the schema.

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 ('Create a new `⬜ OPEN` Work Order in local documentation') plus the linked artifacts (spec anchor, `implements:` files, checklist steps). It explicitly distinguishes itself from `atlas_publish` (finished result) and from `atlas_where` (the index it queries), so an agent can tell the three apart 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 Guidelines5/5

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

Gives an explicit trigger ('when planning a new feature or breaking a user request into structured steps before coding') and an explicit contrast with the nearest alternative ('Unlike `atlas_publish` (which records a finished result)'). The downstream constraint that steps must be checked via `atlas_set_status` before the WO can be done also routes the agent correctly across tools.

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