Skip to main content
Glama

Check the Android wiring

droidmap_check
Read-onlyIdempotent

Runs project-wide checks to list code that compiles but may crash or lose data at runtime across Room migrations, navigation, DI, WorkManager, and manifest issues. Use after edits.

Instructions

Run droidmap's rules on the whole project and list what compiles but would crash or lose data at runtime: Room (missing or failing migrations, schema files out of date, untested migration steps), navigation (routes nothing registers, missing arguments, route types without a NavType, deep links no intent filter accepts), Hilt and Koin bindings, WorkManager setup and inputs, manifest components, permissions, Intent extras and notification channels, DataStores and databases built more than once, Gson and Moshi models that R8 renames, and Gradle module rules and cycles. Use it after editing to confirm nothing new broke; use droidmap_diff for what a change touches and droidmap_explain for how to fix a finding. Read-only and local: it reads the source files, never runs Gradle or the app, and sends nothing anywhere. Findings recorded in the project's droidmap-baseline.json are left out, with a note saying how many. Returns plain text: each finding's severity, rule id and file:line, then the problem, and a count by severity at the end; or "No findings."

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": "droidmap_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
min_severityNoLeave out findings less severe than this: 'error' lists only errors, 'warning' errors and warnings, 'info' (the default) everything.info

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • addedInput schema / properties / min_severity / default
      Added value: +"info"
    • changedInput schema / properties / min_severity / description
      Previous value: -"Only show findings this severe or worse (default: info)."New value: +"Leave out findings less severe than this: 'error' lists only errors, 'warning' errors and warnings, 'info' (the default) everything."
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations it discloses that it never runs Gradle or the app, sends nothing anywhere, and silently suppresses findings recorded in droidmap-baseline.json with a count. That baseline-filtering behavior is a non-obvious result-shaping detail, and the 'never runs Gradle' clause adds real content beyond readOnlyHint/openWorldHint.

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?

The verb and scope are front-loaded, and the closing sentences cover usage and return format efficiently. The long middle enumeration of rule families is dense and could be trimmed, though it does help an agent judge coverage.

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?

With no output schema, the description supplies the return contract itself: severity, rule id, file:line, problem text, severity counts, or 'No findings.' Combined with suppression behavior and the no-Gradle execution guarantee, an agent has everything needed to call and interpret it.

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 the single min_severity parameter already carries a full enum description with default, so the schema does the work. The description adds no additional meaning about severity semantics; baseline 3 applies.

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?

It states a specific verb and resource -- 'Run droidmap's rules on the whole project' -- and then enumerates the exact defect classes it detects (Room migrations, navigation routes, Hilt/Koin, WorkManager, manifest, Gradle cycles). It explicitly distinguishes itself from droidmap_diff and droidmap_explain by naming the sibling it is not.

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?

It gives an explicit trigger ('use it after editing to confirm nothing new broke') and routes two adjacent needs to named alternatives: droidmap_diff for change impact and droidmap_explain for remediation. Nothing about when to pick this tool 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.