Skip to main content
Glama

Map what a change touches

change_map
Read-only

Map code changes for review: see what changed in functions, calls, callers, and security checks, with a read/skim/skip plan and flags for human attention.

Instructions

Map what a code change touches, to review it: every changed Python or TypeScript/JavaScript function, method or class with its old and new code, calls added and removed, calls that only moved into a helper, its callers (with call lines, and whether each caller was updated), removed security checks and access checks, breaking or compatible signature changes, changed module values and the functions using them, and a review plan: read first, read, skim, or skip (skip only when the logic is proven the same: docstring only or local names only; moved code is skim because its import path changed), with changed-line counts and tests whose expected answers changed. Flags list what a person must look at.

Computed from the code, not by a model: the same commit gives the same map. Returns JSON. Read-only and local.

Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "change_map"
  }
}

Input Schema

NameRequiredDescriptionDefault
baseNoCompare with the merge base of this git ref, e.g. origin/main. Default HEAD: only uncommitted changes.HEAD
pathNoProject directory. A relative path resolves against the MCP server's working directory..

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.1.2

TDQS

A4/5.0
Behavior5/5

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

Goes well beyond the readOnly/openWorld/destructive annotations: states results are computed from code rather than model-generated and are therefore deterministic per commit, that output is JSON, that it runs locally and sends nothing to Skylos Cloud, that it needs no SKYLOS_API_KEY, and that there is no daily limit. Those are exactly the operational facts an agent needs before choosing a tool and sizing a loop.

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?

Purpose is front-loaded in the first clause and the operational guarantees are grouped at the end, so the structure is sound. The middle is a long comma-chained enumeration of return contents plus one slightly orphaned sentence ('Flags list what a person must look at'), which is dense but dense with selection-relevant information rather than filler.

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 a two-parameter read-only analysis tool, everything actionable is present: determinism, locality, auth/rate-limit independence, output format, and the semantics of the review-plan tiers. An output schema exists, so the enumerated return values are bonus context for tool selection rather than a required burden.

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% and both parameters carry full descriptions including defaults (base=HEAD for uncommitted changes, path=relative to server cwd), so the schema already does the work. The description adds only indirect context ('reads the repository on this machine', 'the same commit gives the same map' implies base semantics) and nothing on base/path syntax. Baseline 3 is correct.

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?

Opens with a specific verb+resource ('Map what a code change touches, to review it') and then enumerates the exact artifacts produced: changed functions/classes with old/new code, added/removed calls, callers, removed security checks, signature changes, and a review plan with severity tiers. An agent knows precisely what this returns. It stops short of a 5 because it never names the neighbouring tools (validate_code_change, verify_change) it should be preferred over, so differentiation must be inferred from the output inventory.

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?

'to review it' implies the review-a-change context, and the review-plan sentence explains how to interpret the output ('skip only when the logic is proven the same'). However, there is no explicit when-to-use/when-not guidance and no statement of how this differs from the sibling verification tools, so the routing decision is left to inference.

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