find_jni_methods

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

With no annotations, the description carries the burden of behavioral disclosure. It explains what the tool searches for and frames it as the Android reverse-engineering entry point, and it adds session-lifecycle and anti-fabrication rules. However, it does not describe output format, failure behavior, or potential 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 cluttered with repeated tags, emojis, and dupliced trigger scenarios. The core function is buried among meta-instructions; a tighter two-sentence definition would serve agents better.

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 single-parameter tool with no output schema, it covers what the tool does, when to call it, prerequisites, and session hygiene. It does not specify the return format, but the list output is implied and session creation is covered by sibling tools like r2_open_file and r2_close_session.

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%, so baseline is 3, but the description adds lifecycle/precondition meaning: session_id must be tied to a real absolute path, must not be fabricated, and must be closed when no longer used. It does not explain how to obtain the session_id, but it does add value beyond the schema.

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 identifies the tool as JNI method discovery for Android binaries, specifically listing static exported 'Java_' symbols and 'JNI_OnLoad' functions. This distinguishes it from generic siblings like r2_list_functions or r2_disassemble by naming the exact artifact and entry-point purpose.

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?

Explicit trigger scenarios are given (binary analysis, disassembly, debugging, vulnerability research), plus a mandatory-precedence rule requiring this tool for such tasks. It also states prerequisites like confirming an absolute file path and not fabricating results, though it does not explicitly name sibling alternatives or when not to use it.

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