Skip to main content
Glama

steps

Read-onlyIdempotent

Builds an ordered, non-executed work plan for one file, covering its route and checks shaped by tier, change class, and runtime.

Instructions

Build an ordered work plan for one file, including its route and checks; no steps are executed. Tier, change class and runtime shape the plan. Use mind_plan for change classification and isolation guidance. Successful structured results include the command record and exit code.

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": {
      "path": "<path>"
    },
    "name": "steps"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesExisting path, absolute or relative to the client directory.
tierNoscaffolding for the model's size: small adds a work loop and a scope fencemid
changeNoa key of verification_policy/profilessource_change
runtimeNoa runtime_entry id (cursor, claude, openai_codex, hermes, ...). Empty: resolve from HEADRON_AGENT / host signals

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.63.0
    • changedInput schema / properties / path / description
      Previous value: -"path"New value: +"Existing path, absolute or relative to the client directory."
  2. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false. The description adds useful context beyond those annotations: no steps are executed, tier/change/runtime shape the plan, and successful structured results include the command record and exit code.

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?

The description is front-loaded and compact, with four sentences that each contribute distinct information: scope, non-execution, shaping inputs, alternative tool guidance, and result note. There is no redundant or filler wording.

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 the rich annotations, complete parameter schema, and absence of an output schema, the description covers what the tool does, what it does not do, how inputs shape the plan, where to go for related classification, and what successful results include.

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 parameters are already well documented. The description adds that tier, change class, and runtime shape the plan, but does not add syntax or default details beyond what the schema provides.

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 ('Build') and artifact ('ordered work plan for one file'), including scope (route and checks) and the key non-behavior that no steps are executed. This distinguishes it from execution-oriented siblings and points to mind_plan for related classification work.

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?

Explicitly redirects change classification and isolation guidance to mind_plan, giving a clear alternative for related work. It does not enumerate every sibling alternative, but the usage context is clear enough for an agent to select this planner correctly.

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