Skip to main content
Glama

watcher_start

Start a headless hot-folder watcher to automatically run a specified recipe whenever a PDF is dropped into a local directory, enabling automated document processing.

Instructions

Start a headless hot folder watcher daemon on a local directory. When a PDF is dropped into the watched directory it automatically runs the specified recipe.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "dir": "<dir>",
      "recipe": "<recipe>"
    },
    "name": "watcher_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
dirYesAbsolute path to the directory to watch
recipeYesLocal .ppflow recipe path, preset ID, or serialized workflow
output_dirNoOutput directory; defaults to a separate processed subfolder
name_templateNoOutput basename template; input, UTC date, SHA-256 and index tokens
settle_delay_msNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden and does disclose meaningful behavior: the watcher is headless, runs as a daemon, and auto-invokes the recipe on PDF arrival. However, it omits lifecycle details such as whether the call returns immediately or blocks, whether a handle/ID is returned for later watcher_stop, persistence across restarts, and whether duplicate watchers on the same directory are permitted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with no waste; the action and the triggering behavior are front-loaded, letting an agent understand the tool at a glance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given five parameters, no annotations, and no output schema, the definition covers what the tool does but not the operational contract: no return-value expectations, no lifecycle/cleanup story, and no error or conflict behavior for a long-running daemon. Adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 80%, so the baseline is 3, and the description adds slight value by framing 'dir' as the watched local directory and 'recipe' as the workflow triggered on each PDF. It says nothing about output_dir, name_template, or settle_delay_ms, but those are already documented in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Start a headless hot folder watcher daemon on a local directory,' then adds the trigger behavior (PDF dropped → recipe runs). This clearly separates it from watcher_stop and watcher_list by verb, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the trigger description ('when a PDF is dropped'), but there is no explicit guidance on when to prefer this over one-shot tools like document_workflow or batch_fill, and no note that the watcher must later be stopped with watcher_stop.

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