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

Annotations already declare read-only, idempotent, and non-destructive. The description reinforces these traits and adds the prerequisite that workspaceDir must point to a decompile_apk output with AndroidManifest.xml and smali structures, plus hints at the return contents (warnings, securityAnalysis, candidate hooks). No contradictions with annotations.

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

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

Two sentences with no filler: the first front-loads the action and outputs, the second gives usage guidance and prerequisites. Every sentence contributes, and the structure is easy to parse quickly.

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

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

With a single, fully documented parameter and an output schema present, the description provides the necessary workflow placement and tells the agent what to do with the results (review before injection). Nothing essential for correct invocation is missing.

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

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

Schema description for workspaceDir already fully specifies it as a path to a decompiled APK directory produced by decompile_apk. The description restates this requirement but adds no new semantic meaning. With 100% schema coverage, the baseline of 3 is appropriate; the redundancy does not hurt but adds little.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Perform static bytecode analysis and security auditing on a decoded APK workspace') and enumerates exact outputs (manifest components, ABI coverage, JNI loading hooks, native libraries, anti-debug/root checks, candidate injection hooks). It also distinguishes itself from siblings by positioning itself as the audit step between decompile_apk and inject_flutter_runtime_and_smali.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use it: 'Use after decompile_apk to audit the target before modifying files' and routes to the next step: 'review returned warnings, securityAnalysis, and candidate hooks before selecting an injection mode with inject_flutter_runtime_and_smali.' This gives clear context and names the relevant alternative.

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

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

The description transparently discloses side effects beyond annotations, such as 'completely recreates outputDir' and 'automatically installing a dedicated AGENTS.md workspace contract', which align with the destructiveHint=true. It also clarifies that the source APK is not mutated, providing a clear picture of the tool's impact.

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

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

The description is a single dense sentence that front-loads the main purpose and then details usage and side effects. It is appropriately sized for the complexity, though the long run-on structure could be slightly improved for readability, but it remains clear and efficient.

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

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

Given the tool's complexity (3 parameters, side effects, and integration with a workflow), the description covers all essential aspects: purpose, prerequisites (Java and apktool), parameter options, side effects, and next-step guidance. It is complete enough for an agent to understand when and how to use it.

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

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

The schema descriptions already fully cover all three parameters (apkPath, outputDir, decompileSources) with clear explanations. The description restates the decompileSources toggle but adds no new semantic information beyond what the schema provides, so it meets the baseline for full schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's primary function: disassembling Android APK files into Smali code, manifest, assets, and resources, plus installing an AGENTS.md contract. This distinguishes it from sibling tools like analyze_injection_surface and inject_flutter_runtime_and_smali, which have different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides guidance on when to use this tool, including the decompileSources option for asset-only vs. full source disassembly, and explicitly directs the agent to invoke analyze_injection_surface next. It could be more explicit about when not to use it relative to other tools, but the workflow hint and option details offer useful context.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, but the description adds crucial context: requires no authentication, and omitting sessionId returns the active singleton session without error. This goes beyond the structured data and informs the agent about auth and default behavior.

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

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

The description is two sentences, front-loaded with the primary purpose and then usage guidance. It is efficient, with no filler or redundant phrasing.

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

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

With an output schema present, the description needn't detail return format. The tool is simple (one optional param, read-only), and the description covers purpose, usage, auth, and default behavior. Nothing critical is missing for an agent to call it correctly.

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

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

There is only one optional parameter with 100% schema description coverage. The schema already explains that omission returns the default active singleton session. The description repeats this in behavioral transparency but doesn't add new parameter-specific meaning beyond the schema, so a baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Retrieve') and resource (Hermes+ persona, skill sheets, pipeline telemetry, session memory snapshot). It also names siblings (query_memory_graph, update_agent_memory) for differentiation, so an agent can immediately tell this from the other memory tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (start of engineering workflow, inspect pipeline status) and when not (use query_memory_graph for targeted lookups, update_agent_memory for persistence). This is clear, actionable guidance that reduces mis-selection.

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

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

The description openly discloses that the tool mutates workspaceDir in-place, writes Smali classes, copies native libraries, and deploys assets. This aligns with the destructiveHint annotation and leaves no ambiguity about side effects. It also notes the experimental nature of view_tree_injection.

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

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

The description is a single, dense paragraph that packs all essential information without redundancy. It flows logically from action to inputs to mode selection, and every sentence contributes to the agent's understanding.

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

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

Given the complexity of the operation (7 parameters, nested objects, enum, destructive action), the description covers all relevant aspects: prerequisites, side effects, mode selection, fallback behavior, and configuration options. It is sufficiently complete for an agent to invoke it correctly.

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

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

The schema provides 100% coverage with descriptive text for every parameter, including nested fields like methodChannelBridge. Each parameter's purpose, defaults, and allowed values are clearly explained, leaving no ambiguity for the agent.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: injecting a synthesized Flutter payload and Smali bootstrap classes into a decompiled APK workspace. It also names the required inputs (workspaceDir and payloadDir) and distinguishes from sibling tools by referencing their outputs (decompile_apk, synthesize_flutter_payload).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on when to use each injection mode (e.g., prefer activity_overlay for cached-engine screens, direct_application_hook for custom Application classes) and when to enable nativeLibraryFallback to protect against missing ABI crashes, directly helping the agent choose parameter values appropriately.

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

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

The description explicitly states it mutates AndroidManifest.xml in-place, which aligns with the destructiveHint annotation. It does not detail all side effects, but the in-place mutation warning and explicit destructive hint are sufficient for expected use.

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

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

The description is dense but well-structured: first sentence gives the primary purpose, second details parameters and usage. Every phrase contributes essential information, and the most important action (mutates in-place) is front-loaded.

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

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

Given the tool's complexity with seven parameters and an output schema, the description covers the operation, mutation behavior, sequencing, and alternatives. No critical context for correct invocation is missing.

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

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

Schema already covers all parameters with descriptions, so baseline is 3. The description adds meaningful context by explaining how parameters map to manifest modifications (e.g., customApplicationClass rebinds android:name, additionalPermissions inserts uses-permission tags, workspaceDir is modified in-place).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it configures AndroidManifest.xml in a decoded workspace, with specific actions like injecting Flutter activities, rebinding application class, and adding permissions. It distinguishes from siblings by positioning after inject_flutter_runtime_and_smali and before packaging, and explicitly contrasts with analyze_injection_surface.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit sequencing: use after inject_flutter_runtime_and_smali and before packaging. Also gives a clear alternative (analyze_injection_surface) when no changes are needed, which makes tool selection unambiguous.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral specifics beyond that: fuzzy substring matching on the query and ranked results by match score. It also reiterates non-mutating and idempotent, which is consistent. The extra details about matching behavior add value beyond the annotations.

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

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

Three sentences with no redundancy. The purpose is front-loaded, usage guidance follows, and no filler. Highly efficient and well-structured.

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

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

The description covers purpose, usage alternatives, behavioral traits, and the single parameter is well-documented in the schema. Output schema exists, so return format is not needed. Complete for a read-only search tool.

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

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

Schema coverage is 100% and the single parameter 'query' has a descriptive schema entry listing what it matches (package names, launcher activities, etc.). The description adds 'fuzzy substring matching' which slightly extends semantics, but it's a minor addition. Baseline of 3 is appropriate given the schema already carries the meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Search and inspect') and resource ('memory graph'), lists the data types it covers (patch logs, register allocations, etc.), and explicitly names sibling tools (get_agent_context, update_agent_memory) to distinguish itself. The title reinforces the search function. Clear differentiation from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs when to use this tool (locate specific patch records, hook locations, or components by keyword) and provides two alternatives: get_agent_context for a full session snapshot and update_agent_memory to store new observations. This is a model of usage guidance, leaving no ambiguity.

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

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

Annotations already declare destructiveHint=true, and the description adds crucial behavioral details: 'Mutates the filesystem by overwriting outputApkPath and creating temporary alignment artifacts' and mentions the specific signing schemes (v1-v4). It also notes the requirement for a valid workspaceDir. This goes beyond the annotation by specifying what is overwritten and the auto-signing fallback, though it does not mention permissions or error conditions, which are less critical.

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

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

The description is moderately long but well-structured: it opens with the core action, then notes side effects, prerequisites, and optional keystore behavior. Every sentence contributes meaningful information—there is no filler. It could be slightly shorter, but the content justifies the length, and the most important information is front-loaded.

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

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

Given the tool's complexity (multiple build steps, filesystem mutation, optional signing config) and the presence of an output schema (which covers return values), the description covers the essential operational aspects: what it does, side effects, prerequisites, and keystore behavior. It lacks explicit failure modes or environment dependencies, but these are not critical for an agent to call the tool correctly. The description is complete enough for safe invocation.

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

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

Schema description coverage is 100%, so each parameter is already documented. The description reinforces the purpose of workspaceDir and outputApkPath but adds little new semantic meaning beyond the schema. It does clarify the keystoreConfig fallback behavior, but that is also present in the schema ('If omitted, an auto-generated debug keystore is used'). Therefore, the description adds minimal extra value over the schema, warranting a baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs and resources: 'Rebuild a modified decoded workspace with apktool, 4-byte align the uncompressed APK with zipalign, and cryptographically sign the binary with apksigner.' It distinguishes from siblings like decompile_apk by describing the build/sign step. The scope and inputs/outputs are explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context by stating it 'requires a valid workspaceDir containing modified Smali and AndroidManifest.xml', which indicates it should be used after patching. It also explains the behavior when keystoreConfig is omitted (auto-signed debug artifact), guiding whether to pass custom keystore. While it doesn't explicitly name alternative tools, the prerequisites and output clearly position it as the final build step, so usage is reasonably clear.

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

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

Annotations declare destructiveHint=true and readOnlyHint=false. The description goes beyond by specifying exactly what destructive behavior occurs: 'overwrites existing destination files'. It also discloses that it invokes the local Flutter CLI and writes to outputDir or system temp if omitted, adding valuable behavioral context not in the annotations.

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

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

Four sentences with no waste: purpose, mechanics, requirement, and usage instructions. The purpose is front-loaded, and the downstream chaining is mentioned early, making it easy for an agent to scan and understand the tool's role.

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

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

The description covers purpose, prerequisites, parameter usage, and integration with the pipeline (analyze_injection_surface and inject_flutter_runtime_and_smali). An output schema exists, so return values need not be described. Nothing an agent needs to call it correctly is missing.

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

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

Schema covers 100% of parameters, but the description adds practical, cross-tool semantics: it tells the agent to select targetAbis based on analyze_injection_surface and explains buildMode choices ('release' for AOT production, 'debug' for JIT), which enhances the schema's default enum descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states exactly what the tool does: compiles a Flutter project into native libraries (libflutter.so, libapp.so) and flutter_assets partitioned by ABIs. It explicitly references the downstream tool inject_flutter_runtime_and_smali, distinguishing it from siblings like decompile_apk and analyze_injection_surface.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on when and how to use: 'Set targetAbis to match the target APK architectures discovered via analyze_injection_surface', 'choose buildMode ('release' for AOT production, 'debug' for JIT)', and 'forward the emitted payloadDir to inject_flutter_runtime_and_smali'. It also states the prerequisite that flutterProjectPath must contain pubspec.yaml.

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

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

Annotations already declare destructiveHint=true, but the description adds significant behavioral detail: it mutates in-memory state, persists to .mcp_memory/session_state.json, merges non-null fields, appends notes, and logs verified patch entries when patchType and patchDetails are provided. This goes well beyond the annotations and gives the agent a precise mental model of side effects.

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

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

The description is two dense, front-loaded sentences. The first sentence states purpose and behavior, the second gives usage context. Every clause earns its place; no filler or redundancy. The structure is ideal for quick agent parsing.

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

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

For a tool with 7 parameters, 0 required, and an output schema, the description covers the essential context: what it does, when to use it, how it behaves, and the exact persistence path. It does not waste space explaining return values (output schema handles that). Nothing critical is missing for correct invocation.

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

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

While the schema covers all 7 parameters with descriptions (100% coverage), the tool description adds interaction semantics: 'non-null fields merge into state' and 'notes are appended' clarify how parameters combine, and it explains the patchType+patchDetails pairing for logging. This is meaningful beyond the schema, though the baseline is already 3 due to high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'update' and the resource 'active reverse-engineering session memory', and enumerates the specific content types (notes, workspace metadata, patch history). It also differentiates from siblings by explicitly naming get_agent_context and query_memory_graph as inspection alternatives, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance: 'Use after manual Smali edits, manifest changes, or decompiler discoveries to keep agent telemetry synchronized.' It also states when NOT to use it ('use get_agent_context or query_memory_graph instead when inspecting memory without modification'), providing clear alternatives and exclusions.

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