Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Delimit Diagnose

delimit_diagnose

Run a full health check on a Delimit installation to diagnose connectivity, permissions, API keys, and configuration drift, with optional dry-run preview and undo.

Instructions

Comprehensive health check of the Delimit installation (delimit doctor).

When to use: as the universal first-step diagnostic when something isn't working — covers MCP connectivity, deps, governance state, AI assistants, permissions, API keys, network, version, daemons, disk. When NOT to use: for repo-level health (use delimit_repo_diagnose) or first-run discovery (delimit_quickstart).

Sibling contrast: delimit_repo_diagnose checks one repo; this checks the Delimit installation as a whole.

Side effects: in normal mode, fixes some configuration drift (writes a doctor-manifest.json so later --undo can revert). dry_run=True is read-only and previews changes. undo=True reverts changes from the last doctor run using the saved manifest.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
undoNoIf True, revert changes from the last run.
dry_runNoIf True, preview changes without executing.
project_pathNoProject to diagnose. Default "." (cwd)..

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv4.7.9
    • changedInput schema / properties / dry_run / description
      Previous value: -"If True, return a preview of what doctor would create/modify without executing changes."New value: +"If True, preview changes without executing."
    • changedInput schema / properties / project_path / description
      Previous value: -"Project to diagnose."New value: +"Project to diagnose. Default \".\" (cwd)."
    • changedInput schema / properties / undo / description
      Previous value: -"If True, revert changes from the last doctor --fix run using the saved manifest."New value: +"If True, revert changes from the last run."
  2. Changed3 schema fields changedv4.5.5
    • addedInput schema / properties / dry_run
      Added value: +{
+  "default": false,
+  "description": "If True, return a preview of what doctor would create/modify without executing changes.",
+  "type": "boolean"
+}
    • addedInput schema / properties / project_path / description
      Added value: +"Project to diagnose."
    • addedInput schema / properties / undo
      Added value: +{
+  "default": false,
+  "description": "If True, revert changes from the last doctor --fix run using the saved manifest.",
+  "type": "boolean"
+}
  3. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

The description goes well beyond the annotations by disclosing side effects: normal mode can fix configuration drift, writes a doctor-manifest.json for reversibility, dry_run=True is read-only, and undo=True reverts the last run. This is exactly the behavioral context an agent needs for a mutating diagnostic tool.

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?

The description is well-structured with clear labeled sections: purpose, when to use, when not to use, sibling contrast, and side effects. Every sentence carries information, and the most important purpose statement is front-loaded.

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 multiple modes and side effects, the description covers scope, alternatives, behavior, reversibility, and read-only mode. An output schema exists, so return-value documentation is not the description's responsibility. Nothing critical is missing for correct invocation.

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 the baseline is 3. The description adds useful meaning by explaining that dry_run is read-only and previews changes, and that undo uses the saved manifest to revert. It does not add detail about project_path beyond the schema, but the schema already documents it clearly.

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?

The description opens with a specific verb-resource pair: 'Comprehensive health check of the Delimit installation (delimit doctor).' It also explicitly distinguishes itself from delimit_repo_diagnose, which checks one repo, so an agent can tell them apart immediately.

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?

It provides an explicit 'When to use' section naming the universal first-step diagnostic context, plus a 'When NOT to use' section naming two alternatives (delimit_repo_diagnose and delimit_quickstart). This gives clear decision rules with no ambiguity.

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