eazy-ba
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ba_initD | Scaffold the docs/ba BA docs tree. |
| ba_session_startA | Start or resume a BA session (mode: discovery | stabilize | change | ground). For ground mode, pass readScope: the user-supplied paths/globs (relative to projectRoot) the BA may read; it is persisted to the session and bounds what ba_ground can auto-accept. |
| ba_assessB | Analyze current state and return the questions to ask the user. Writes no BA documents (it only updates session state). |
| ba_record_answersC | Record the user's answers as traceable decisions. |
| ba_applyB | Materialize/update documents from recorded decisions. Every artifact must cite derived_from decisions. |
| ba_statusB | Report open questions, gaps, pending decisions, the open coverage plan, and stability. |
| ba_planA | Declare or retire agent/user coverage topics (the visible, steerable coverage plan on top of the floor). Declaring is idempotent; retiring stops a topic from gating stability. Returns the current open plan. |
| ba_finalizeA | Promote every draft BA document (persona/fr/nfr/use-case/story/glossary/tech-surface) to status 'reviewed' in one batch — the clean 'here are your docs' step. Idempotent and repeatable: a second call with nothing in draft is a no-op, and it promotes again after a change loop re-opens work. Only changes status; never touches backing. Returns what was promoted. |
| ba_impactA | For a mid-project change: report blast radius, conflicts, severity, consequences, and change questions for the given target ids. Creates nothing. |
| ba_groundA | Ground flow (ground session only): record code observations the host agent read. Each is { fact_kind, claim, anchors }. Auto-accepts ONLY existence facts the server can re-verify (entity-exists | dependency-present) whose anchors resolve on disk and sit inside the session read scope — recorded as confirmed/code-verified. Everything else (route/middleware/config-key, anything mislabeled, out-of-scope or unresolvable anchors) is recorded as an inferred+open observation that the user must confirm. Idempotent by (anchors+claim). |
| ba_getC | Get one artifact by id. |
| ba_listC | List artifacts filtered by type/status/priority/tag. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool has a distinct purpose: e.g., ba_assess queries state, ba_record_answers stores user decisions, ba_impact analyzes change effects. No two tools overlap in functionality, making selection unambiguous.
All tools follow a consistent 'ba_verb_noun' pattern with snake_case (e.g., ba_session_start, ba_record_answers). No mixing of conventions or inconsistent verb styles.
With 12 tools covering multiple BA modes (discovery, stabilize, change, ground), the count is well-scoped. Each tool serves a clear step in the workflow without bloat or missing essentials.
The set covers the full BA lifecycle: session management, assessment, decision recording, artifact materialization, finalization, querying, planning, and impact analysis. Minor gap: no explicit tool for direct manual artifact creation, but the workflow via decisions and finalization covers it.