apsa

Overview Schema Source Related Servers Discussions Admin

audit_start

Start a persistent offline audit to inspect Android APKs and iOS apps without installation or merging, using device info and configuration.

Instructions

Start a persistent offline audit. APKS requires apk_set_device with sdkVersion, supportedAbis, screenDensity and supportedLocales; selected APKs are inspected individually without installation or manifest/resource merging. ipa_trust_policy supplies explicit digest-bound DER anchors for cryptographic chain checks only, without Apple signer identity, revocation or app authenticity verification. Configuration selects a relative manifest or .plist without build-system merge. dependency_module and runtime_configuration select recorded Gradle lock resolution; optional dependency_evidence paths narrow it, without verifying freshness or installation. specs declares project sources/sinks. Use jobs_status for progress and jobs_cancel to stop it.

Input Schema

Name	Required	Description	Default
`sbom`	No
`specs`	No
`target`	Yes
`device_info`	No
`configuration`	No
`source_module`	No
`apk_set_device`	No
`ipa_trust_policy`	No
`dependency_module`	No
`dependency_evidence`	No
`runtime_configuration`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv1.6.0Oct 18, 2026

addedInput schema / properties / apk_set_device

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Apk Set Device"
+}

addedInput schema / properties / dependency_evidence

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Dependency Evidence"
+}

addedInput schema / properties / dependency_module

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Dependency Module"
+}

addedInput schema / properties / ipa_trust_policy

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Ipa Trust Policy"
+}

addedInput schema / properties / runtime_configuration

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Runtime Configuration"
+}

Changed3 schema fields changedv1.5.1Oct 12, 2026

addedInput schema / properties / configuration

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Configuration"
+}

addedInput schema / properties / source_module

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Source Module"
+}

addedInput schema / properties / specs

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Specs"
+}

First observedv1.0.3Oct 6, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false. The description adds substantial behavioral context beyond that: APKs are inspected individually without installation or manifest/resource merging, ipa_trust_policy anchors are for cryptographic chain checks only (no signer identity, revocation, or authenticity verification), and configuration does not undergo build-system merge. These 'what it deliberately does not do' statements are exactly the kind of disclosure annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, which is good, but the parameter explanation is one dense run-on block of semicolon-separated clauses with no structure. Every clause carries information, yet the lack of segmentation makes it hard to scan for a specific parameter.

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

Completeness3/5

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

An output schema exists, so return values need not be covered, and the description handles most of the 11 parameters plus follow-up tools. However, for an 11-parameter tool with 0% schema coverage, the unexplained 'target' (the only required parameter), 'sbom', 'device_info', and 'source_module' leave a real gap.

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 description coverage is 0%, so the description must compensate and largely does: it explains apk_set_device's required sub-fields (sdkVersion, supportedAbis, screenDensity, supportedLocales), the semantics of ipa_trust_policy, configuration, dependency_module, runtime_configuration, dependency_evidence, and specs. It leaves sbom, target, device_info, and source_module unexplained, so compensation is incomplete.

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?

The opening sentence gives a specific verb and resource ('Start a persistent offline audit') and the 'persistent/offline' qualifier is meaningful scoping. It does not explicitly differentiate itself from the sibling audit_scan, so an agent must infer the distinction rather than being told.

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?

It names follow-up tools ('Use jobs_status for progress and jobs_cancel to stop it'), which is useful routing, but never states when to choose audit_start over audit_scan, specs_validate, or dependency_check. Usage is implied by the parameter descriptions rather than stated.

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