Monitor file and directory changes on Linux by adding inotify kernel watches. Set target path, filter specific events, or watch recursively to enable real-time file activity alerts for system control.
Add a Linux inotify kernel watch on a file or directory.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Target path. | |
| events | No | Event mask or comma-separated list. | all |
| recursive | No | Recursive watch flag. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description carries full burden. It states the action but does not disclose that the tool is non-blocking, returns a watch descriptor, or that the watch persists until removed. It also does not mention whether the watch is registered globally or per session, which is critical operational context for an agent.
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, clear sentence with no redundancy. It is efficiently structured, though it could be expanded slightly without becoming verbose.
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?
Without annotations or an output schema, the description fails to provide enough context. An agent does not know how this tool fits into the inotify workflow (e.g., that watches must be created before events can be read), nor what the return value is. The description is too minimal for correct usage.
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 parameters (path, events, recursive) already have descriptions. The tool description adds no extra meaning about the parameters beyond the target being a file or directory, which is redundant with the schema. Baseline 3 applies because the schema covers the details.
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 a specific verb ('Add') and resource ('Linux inotify kernel watch') with a target ('file or directory'). It clearly indicates the action and resource, but does not explicitly differentiate from sibling tools like inotify_wait_event or inotify_read_events, though the verb 'add' distinguishes from list/read/unwatch 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?
No guidance is provided on when to use this tool versus the sibling inotify tools. There is no mention that this tool only sets up the watch and that one must later call inotify_read_events or inotify_wait_event to consume events. The intended usage context is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.