frida_install_hook

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

With no annotations, the description carries the burden. It discloses persistence, auto-unload via duration_seconds, message collection via send(), and return of script_id. However, it lacks details on limits, conflicts with other hooks, or behavior on session disconnection.

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 concise with two well-structured paragraphs. Parameter list is clear and each sentence serves a purpose. No extraneous information.

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?

Covers prerequisite, parameters, return value, and event retrieval. Absence of output schema is mitigated by explaining script_id and related tools. Could mention that hook persists until unloaded or session ends, but still adequate.

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?

Despite 0% schema coverage, the description explains each parameter: js_code (Frida JS with send), name (optional label, default 'hook_N'), duration_seconds (auto-unload, 0=forever). This adds significant meaning beyond the schema's type info.

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 'Install a persistent hook that stays active and collects messages.' This distinguishes it from other hook tools like frida_hook_native_function or frida_uninstall_hooks by emphasizing persistence and message collection.

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?

It specifies a prerequisite ('Requires an active session') and mentions how to retrieve hook events, but does not explicitly contrast with alternatives or state when not to use this tool. Some guidance is present but not comprehensive.

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