Skip to main content
Glama
Sign In
musterd

musterd

Official
by musterd-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

lane_open

Declare a unit of work as a lane with its title, touched paths, and dependencies; optionally claim ownership and get advisory contention warnings without blocking progress.

Instructions

Declares a unit of work as a lane: title, the paths it touches, what it builds on. claim:true takes ownership when the work is yours. Returns the lane + advisory contention warnings (unmet dependency, surface overlap) — never blocking.

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": {
      "title": "<title>"
    },
    "name": "lane_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
riskNoonly user-facing: peer review. Other tag, e.g. policy: human. [] = none.
roleNoassignment hint (advisory)
areasNodeclared areas; replace those derived from scope (ADR 582)
claimNoown it yourself now (recommended at task start)
scopeNopaths this lane touches, e.g. ["packages/server/src/store/**"]
titleYesthe work-item, short
branchNogit branch carrying the work
detailNoacceptance criteria / notes
stakesNohow much this is worth someone’s eyes (default normal). Declared, not inferred from the files; a low lane may be exempted from acceptance (ADR 234)
goal_idNolink this lane to a Goal (team_next groups by it)
projectNosurface-space; defaults to this workspace’s repo
reads_onNo
requestedNo
depends_onNolane ids this lane builds on
source_refNoissue it came from (acme/app#12); one open lane per ref

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.7.1

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the most valuable behavioral fact: the tool returns the lane plus advisory contention warnings (unmet dependency, surface overlap) and is 'never blocking'. It omits other mutation-relevant behavior such as what is created, whether re-opening an existing lane errors, and any authorization or idempotency semantics.

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?

Two sentences, front-loaded with the core verb and then the ownership flag and return contract; there is essentially no filler. Phrases like 'what it builds on' are slightly informal where 'depends_on lane ids' would be crisper, but the density is appropriate.

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

Completeness3/5

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

Telling the agent the return payload matters because there is no output schema, and the non-blocking advisory framing is a genuinely useful addition. But for a 15-parameter mutation tool with a nested object and zero annotations, the description covers only a fraction of the surface, leaving open/claim/error behavior and parameter interactions unexplained.

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 87%, so the schema already documents nearly every one of the 15 parameters. The description paraphrases title, scope ('paths it touches'), depends_on ('what it builds on'), and claim, adding a little interpretive framing but no syntax, defaults, or constraints beyond what the schema states.

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?

The description names a specific verb and resource ('Declares a unit of work as a lane') and enumerates the core inputs (title, paths, dependencies). It implicitly separates the plain-open path from ownership via 'claim:true takes ownership', but never names sibling tools such as lane_claim or lane_update, so differentiation is inferential rather than explicit.

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?

'claim:true takes ownership when the work is yours' gives one conditional usage cue for a key flag. However, there is no guidance on when to open a lane at all versus when to claim/update/submit an existing one, and no exclusions or prerequisites (e.g. one open lane per source_ref) are surfaced in the description despite the team of lane_* siblings.

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

Deploy Server

Other Tools