Frida MCP Server

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'live instances on the heap' and implies a read-only operation, but doesn't specify critical details like whether this requires specific permissions, how results are returned (e.g., format, pagination), potential performance impacts, or error conditions. For a tool with no annotation coverage, this is a significant gap in transparency.

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, efficient sentence that clearly states the tool's purpose without unnecessary words. It's front-loaded with the core action and includes essential context ('on the heap (Android)'). Every part of the sentence earns its place, making it highly concise 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?

Given the complexity (a debugging/memory inspection tool), lack of annotations, no output schema, and low schema description coverage (33%), the description is incomplete. It doesn't cover behavioral aspects like return format, error handling, or prerequisites (e.g., needing an attached session), leaving significant gaps for the agent to operate effectively in a Frida context.

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 description coverage is 33% (only 'class_name' has a description), and the description doesn't add any parameter-specific information beyond what's in the schema. It implies parameters like 'class_name' and possibly 'limit' through context, but doesn't explain their semantics, such as what 'session_id' refers to or how 'limit' affects results. With low schema coverage, the description fails to compensate adequately, resulting in a baseline score.

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: 'Find live instances of a Java class on the heap (Android).' It specifies the verb ('Find'), resource ('live instances of a Java class'), and context ('on the heap (Android)'), making the action clear. However, it doesn't explicitly differentiate from sibling tools like 'frida_java_enumerate_classes' or 'frida_objc_find_instances', which is why it doesn't achieve a perfect score.

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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an active Frida session), exclusions, or comparisons to similar tools like 'frida_java_enumerate_classes' (which lists classes) or 'frida_objc_find_instances' (for Objective-C). This lack of contextual usage information leaves the agent to infer when this tool is appropriate.

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