delimit

Official

by delimit-ai

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Delimit Self Repair Daemon

delimit_self_repair_daemon

Idempotent

Start, stop, or inspect the KPI-watcher daemon that polls function metrics and sends founder alerts when breaches occur.

Instructions

Control the self-repair watcher daemon (LED-191, internal).

When to use: to start, stop, or inspect the watcher that polls function KPIs and emits founder alerts on breaches. When NOT to use: for general daemon status (use delimit_daemon_status) or inbox / social daemons (delimit_inbox_daemon, delimit_social_daemon).

Sibling contrast: delimit_daemon_status is the autonomous loop's daemon; this is the KPI-watcher daemon. Different processes.

Side effects: action="start" / "stop" mutate daemon state. Idempotent start. Circuit-breakered stop after 3 consecutive pass failures. Honors DELIMIT_SELF_REPAIR_PAUSE=1 at every pass without requiring a daemon restart. Higher modes (diagnose / deliberate / apply / verify) chain through the watcher when configured per function in ~/.delimit/self_repair.yaml.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`action`	No	'start' (begin polling), 'stop' (halt polling), 'status' (running / last_pass / breaches_emitted / consecutive_failures).	status

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv4.7.9Jun 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already set readOnlyHint=false and idempotentHint=true, and description adds matching detail: start/stop mutate state, idempotent start, circuit-breakered stop, environment-pause behavior, and mode chaining. It also mentions config path. No contradiction with annotations.

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?

Well structured with labeled sections and front-loaded purpose; all sentences contribute, but it is denser/longer than strictly necessary and could be trimmed without losing key info.

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?

Complete for a one-parameter control tool: covers when, when not, alternatives, side effects, env var, and config path; output schema exists so return values need no description.

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 covers action with 100% coverage; description adds operational consequences for parameter values: start/stop mutate daemon state, idempotent start, circuit-breakered stop. This is beyond schema's 'begin polling'/'halt polling', though status output is only in 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?

Description states a specific verb+resource: control the self-repair watcher daemon, with explicit actions start/stop/inspect and object (KPI watcher emitting founder alerts on breaches). It distinguishes from siblings by naming delimit_daemon_status, inbox/social daemons and noting different processes.

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?

Explicit when-to-use and when-not-to-use sections; names alternative tools (delimit_daemon_status, delimit_inbox_daemon, delimit_social_daemon) and clarifies the sibling contrast. No inference required.

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

Deploy Server