Monitor a directory for file changes over a fixed duration, with optional extension filtering and polling interval.
Watch a directory for changes over a fixed duration (MCP-bound watcher)
| Name | Required | Description | Default |
|---|---|---|---|
| directory | Yes | Directory to watch | |
| extensions | No | Filter by extensions e.g. ['.pdf'] | |
| poll_interval | No | Polling interval in seconds | |
| duration_seconds | No | How long to watch |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and largely fails: it does not say whether the call blocks for the whole duration, what it returns (no output schema exists), how it behaves on timeout, or whether it reports a change count or event list. The parenthetical '(MCP-bound watcher)' is jargon that adds little operational meaning.
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 sentence with the key constraint (fixed duration) front-loaded and no wasted clauses. The trailing '(MCP-bound watcher)' parenthetical is the one element that does not clearly earn its place.
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 blocking, no-annotations, no-output-schema tool, the description is too thin: an agent cannot tell what it receives back, whether the call hangs for the duration, or how changes are surfaced. The schema covers inputs, but the behavioral contract of a watcher is left unspecified.
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%, so directory, extensions, poll_interval, and duration_seconds are all documented in the schema itself. The description adds no syntax, units, or default details beyond what the schema already provides, making the baseline 3 appropriate.
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 ('Watch') and resource ('directory') and adds scope ('over a fixed duration'), so an agent can distinguish it from read_file/list_files/write_file. It does not explicitly name a sibling or contrast itself with them, but the watcher semantics are unambiguous.
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 when-to-use guidance, no prerequisites, and no alternatives are named among the five siblings. The phrase 'over a fixed duration' implies the tool is bounded rather than long-lived, but the agent must infer when polling a directory is preferable to list_files or search_in_file.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.