Create a file system watcher that runs a specified command when watched files change, with optional glob filtering and debounce timing.
Set up a file system watcher that triggers a command when files change
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Directory path to watch | |
| command | Yes | Command to run when files change | |
| pattern | No | Glob pattern to filter (e.g. '*.swift', '*.ts') | |
| debounce_seconds | No | Debounce interval in seconds (default: 2.0) |
Changes observed during successful MCP inspections.
v2.2.5Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description bears the full behavioral burden. It correctly implies a persistent, side-effecting background process that runs arbitrary commands, but omits lifecycle details: whether the watcher survives restarts, whether it needs cleanup via remove_file_watch, and whether anything is returned to identify the watcher later.
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?
A single, well-formed sentence with the core action and trigger condition front-loaded and no filler. Nothing in it could be cut without losing the stated behavior.
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?
This tool spawns a long-lived process that executes arbitrary commands, which is meaningful complexity, yet there are no annotations and no output schema. The description leaves the watcher's lifecycle, return value, and relationship to remove_file_watch/list_file_watches unaddressed.
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%, with each of the four properties documented in the schema itself, so the baseline of 3 applies. The description adds no meaning beyond the schema (e.g., glob semantics, debounce behavior, path constraints).
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 and resource ('Set up a file system watcher') plus its effect ('triggers a command when files change'), so an agent understands exactly what it creates. It does not name its sibling alternatives (remove_file_watch, list_file_watches), so differentiation is only implied by the verb.
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?
There is no explicit when-to-use or when-not-to guidance. The description never says what to do instead if the agent only wants a one-off command run (execute_command) or how this differs from the watch-management siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.