Skip to main content
Glama

Native mobile build plan — Atom

Native mobile build plan

native_mobile_build_plan
Read-onlyIdempotent

Submits a native mobile build-plan record (device constraints and platform citizenship, offline-first and sync, builds and signing, testing and accessibility, release/store and privacy, red lines) and returns a deterministic NATIVE_MOBILE_BUILD_PLAN_READY / NATIVE_MOBILE_BUILD_PLAN_NOT_READY / INSUFFICIENT_EVIDENCE verdict across six sections, including computed per-permission feature-coverage checks, with per-check evidence. Audits the declared build-plan record; it builds no app and submits nothing to any store.

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": "native_mobile_build_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
appNoMobile app under build-plan review.
buildsNoBuilds and signing evidence.
offlineNoOffline-first and sync evidence.
privacyNoPrivacy evidence.
releaseNoRelease and store evidence.
testingNoTesting and accessibility evidence.
red_linesNoRed-line evidence.
constraintsNoDevice-constraint evidence.
permissionsNoDeclared permissions: {name, feature_needing_it}.
platform_citizenshipNoPlatform citizenship evidence.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint, idempotentHint, openWorldHint=false), the description discloses that the verdict is deterministic across six sections, that per-permission feature-coverage checks are computed, and that evidence is returned per check. It also explicitly disclaims side effects ('builds no app and submits nothing to any store'), reinforcing the read-only annotation rather than contradicting it — though the opening verb 'Submits' is slightly at odds in tone with a pure read operation.

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 action and result, followed by scope exclusions. The long parenthetical section list is dense but each item maps to a real schema field, so it earns its space; it could be tightened but nothing is filler.

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

Completeness4/5

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

For a 10-parameter tool with nested objects and no output schema, the description covers the verdict space, the evidence returned, and the no-side-effect boundary, and it points to SERVICE.md for the field table. The only gap is that zero required parameters leave the minimum viable input unstated, with INSUFFICIENT_EVIDENCE only implicitly covering missing sections.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the per-field descriptions already carry the load. The description still adds semantic value by grouping the fields into the six audited sections and by calling out that 'permissions' is used for computed feature-coverage checks, which explains why that parameter exists rather than merely naming it.

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 and resource ('Submits a native mobile build-plan record') and enumerates the reviewed domains: device constraints, platform citizenship, offline/sync, builds and signing, testing and accessibility, release/store/privacy, red lines. It also names the exact return tokens (NATIVE_MOBILE_BUILD_PLAN_READY / NOT_READY / INSUFFICIENT_EVIDENCE), so the agent knows precisely what output to expect.

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?

The closing sentence gives clear scope guidance — 'Audits the declared build-plan record; it builds no app and submits nothing to any store' — which tells the agent this is an evaluation tool, not a build or publish tool. There is no explicit when-to-use trigger or named alternative, but with no siblings and a narrowly scoped domain the implied usage is unambiguous.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.