Skip to main content
Glama

Project Harmony Application Graph

project_harmony_application_graph
Idempotent

Projects authenticated HarmonyOS HAP, HSP, or App Pack evidence into an execution-free inventory of component paths, hashes, packaging hints, and N-API bridge hypotheses.

Instructions

Project authenticated HarmonyOS HAP, HSP, or App Pack inventory Evidence into an execution-free application inventory. Reports packaging-model hints (Stage module.json versus FA config.json), exact component paths and hashes (manifests, Ark bytecode, resources, native libraries, JavaScript, signing), App Pack child packages, runtime-family hints, and path-based N-API bridge hypotheses without decoding Ark bytecode, parsing manifest semantics, or claiming observed runtime calls.

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": {
      "inventory_evidence": "<inventory_evidence>"
    },
    "name": "project_harmony_application_graph"
  }
}

Input Schema

NameRequiredDescriptionDefault
inventory_evidenceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations, the description discloses the analytical posture: execution-free, no Ark bytecode decoding, no manifest semantic parsing, and N-API bridge output is labeled "path-based hypotheses" rather than observed calls. That distinction between derived hints and observed fact is exactly the behavioral context an agent needs, and nothing contradicts readOnlyHint=false, which is consistent with projecting results into an inventory store.

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 verb and resource, and the negative-capability clause is placed where it belongs at the end. The long parenthetical enumerations are information-dense but slightly heavy; they earn their place by telling the agent what the output inventory will contain.

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?

With one complex required parameter and no output schema, the description does the necessary work by describing both input expectations and the shape of the returned inventory (packaging-model hints, component paths and hashes, child packages, runtime hints, bridge hypotheses). Remaining gaps are minor: no guidance on error or partial-coverage behavior and no hint about evidence volume or ordering requirements.

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 0% and the single top-level parameter (inventory_evidence) carries no schema description, so the description must carry the meaning — and it does, by specifying that the parameter expects authenticated HarmonyOS HAP/HSP/App Pack Evidence and enumerating the artifact categories (manifests, bytecode, resources, native libraries, JavaScript, signing) expected within. It does not explain expected evidence granularity or minimum viable payload shape, so it falls short of full compensation.

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?

"Project authenticated HarmonyOS HAP, HSP, or App Pack inventory Evidence into an execution-free application inventory" gives a specific verb (project), a specific resource (HarmonyOS package Evidence), and a specific output (application inventory). The named platform formats make it trivially distinguishable from project_android_application_graph, project_apple_application_graph, and project_managed_application_graph.

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?

It clearly states the applicable input class (authenticated HarmonyOS HAP/HSP/App Pack Evidence) and the negative scope (no Ark decoding, no manifest parsing, no runtime claims), which implicitly rules out use for other platforms or for runtime-trace questions. It stops short of explicitly naming the sibling graph tools as alternatives or stating when a different tool should be preferred.

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