Skip to main content
Glama

Delimit Hot Reload

delimit_hot_reload

Start, stop, or tick a cross-session file watcher that reloads AI tool modules in place so other live Claude sessions pick up changes without an MCP server restart.

Instructions

Control the cross-session MCP hot-reload watcher (LED-799).

When to use: when developing tools and you want other live Claude sessions to pick up changes without an MCP server restart. When NOT to use: for production deployments — hot reload is a development convenience.

Sibling contrast: delimit_swarm reload also reloads modules but in swarm context; this is the cross-session file watcher.

Side effects: action="start" launches a background poller on ai/*.py for new files and mtime changes; matching modules are reloaded in place and new @mcp.tool() decorations are registered against the live FastMCP instance. action="stop" halts it. action="tick" runs a single scan synchronously.

Limitation: edits to ai/server.py itself still require a full restart. Convention: put new tools in ai/tools/.py.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "delimit_hot_reload"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNo"start", "stop", "status" (default), or "tick".status
intervalNoPoll interval in seconds (used on start). Default 2.0.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv4.24.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes well beyond by disclosing that start launches a background poller on ai/*.py, that modules are reloaded in place and new @mcp.tool() decorations registered against the live FastMCP instance, that tick runs a synchronous single scan, and that edits to ai/server.py still need a full restart. That is exactly the side-effect context an agent needs before calling a non-read-only tool.

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

Conciseness4/5

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

Labeled sections (When to use / When NOT to use / Sibling contrast / Side effects / Limitation) make it scannable and front-loaded, with no wasted sentences. The internal ticket reference 'LED-799' is the only line that does not earn its place.

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

Completeness5/5

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

For a tool with a background poller and two parameters, the description covers side effects, a hard limitation, and a placement convention, while annotations and the output schema handle safety profile and return values. An agent has everything needed to call it correctly and to avoid misusing it.

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 100%, so values and defaults are already documented, but the description adds the behavioral effect of each action (start spawns the poller, stop halts it, tick does one synchronous scan) and implies interval applies only on start. Minor gap: the 'status' action is never explained in the prose, only in the schema.

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

Purpose5/5

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

States a specific verb and resource: 'Control the cross-session MCP hot-reload watcher', and explicitly contrasts with the sibling delimit_swarm reload ('this is the cross-session file watcher'). An agent can distinguish the two without opening either schema.

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

Usage Guidelines5/5

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

Provides explicit 'When to use' (developing tools, wanting other live sessions to pick up changes without restart) and 'When NOT to use' (production deployments), plus a named sibling contrast. Nothing about tool selection 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.

Deploy Server

Other Tools