Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Delimit Activate

delimit_activate

Activate Delimit and run a readiness checklist to confirm license, MCP, governance, tests, permissions, and premium are properly set up.

Instructions

Activate Delimit and run a readiness checklist.

When to use: as the post-install confirmation that everything is wired up — license, MCP, governance, tests, permissions, premium. When NOT to use: for diagnostic-style debugging of an already activated install (use delimit_diagnose) or first-run discovery (delimit_quickstart).

Sibling contrast: delimit_diagnose investigates issues; delimit_quickstart is the 60-second guided first run; this is the activation + readiness checklist.

Side effects: applies the license key when provided; auto-configures AI-assistant permissions when auto_permissions=True (writes .claude/settings.json). Skipped checks (premium on free tier, no test framework) do not count against the score.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
license_keyNoOptional license key (e.g. DELIMIT-XXXX-XXXX-XXXX). Empty = free-tier readiness only.
project_pathNoProject directory to check. Default "." (cwd)..
auto_permissionsNoAuto-configure AI assistant permissions (default True).

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 / auto_permissions / description
      Previous value: -"Auto-configure AI assistant permissions for Delimit tools (default True)."New value: +"Auto-configure AI assistant permissions (default True)."
    • changedInput schema / properties / license_key / description
      Previous value: -"Optional license key to activate Pro (e.g. DELIMIT-XXXX-XXXX-XXXX). Leave empty to check free-tier readiness."New value: +"Optional license key (e.g. DELIMIT-XXXX-XXXX-XXXX). Empty = free-tier readiness only."
    • changedInput schema / properties / project_path / description
      Previous value: -"Project directory to check."New value: +"Project directory to check. Default \".\" (cwd)."
  2. Changed5 schema fields changedv4.5.5
    • addedInput schema / properties / auto_permissions
      Added value: +{
+  "default": true,
+  "description": "Auto-configure AI assistant permissions for Delimit tools (default True).",
+  "type": "boolean"
+}
    • addedInput schema / properties / license_key / default
      Added value: +""
    • addedInput schema / properties / license_key / description
      Added value: +"Optional license key to activate Pro (e.g. DELIMIT-XXXX-XXXX-XXXX). Leave empty to check free-tier readiness."
    • addedInput schema / properties / project_path
      Added value: +{
+  "default": ".",
+  "description": "Project directory to check.",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "license_key"
-]
  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 (readOnlyHint=false, destructiveHint=false) by disclosing concrete side effects: it applies the license key when provided, and when auto_permissions=True it writes .claude/settings.json. It also explains scoring semantics — skipped checks (premium on free tier, no test framework) don't count against the score — which is critical behavioral context an agent could not infer from the schema or annotations. This file-write disclosure is especially valuable since destructiveHint=false might otherwise imply no state changes.

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 compact and superbly organized with labeled sections: core purpose first, then When to use, When NOT to use, Sibling contrast, and Side effects. Every sentence earns its place — there is no filler, and the labeled structure makes it trivially scannable for an agent. The length is justified by the tool's complexity (side effects, multiple checks, sibling ambiguity).

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?

This is a mutation tool with real side effects and scoring behavior, and the description covers every angle an agent needs: purpose, usage conditions, exclusions, sibling differentiation, side effects, parameter effects, and handling of edge cases (skipped checks). The output schema exists, so return values need no explanation. Nothing material is missing for correct selection and 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 schema already documents all three parameters with types, defaults, and individual descriptions. The tool description adds genuine semantic value beyond the schema by explaining the behavioral effect of key parameters: license_key 'applies the license key when provided' and auto_permissions triggers the .claude/settings.json write. This links parameters to consequences rather than just formats, earning a 4.

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 first sentence states a specific verb and resource with a concrete outcome: 'Activate Delimit and run a readiness checklist.' The scope is further pinned down by naming the exact areas checked (license, MCP, governance, tests, permissions, premium), which distinguishes it from the vast sibling list. The explicit sibling contrast against delimit_diagnose and delimit_quickstart makes the tool's identity unmistakable.

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?

The description has an explicit 'When to use' section (post-install confirmation that everything is wired up) and a 'When NOT to use' section that names the correct alternatives: delimit_diagnose for diagnostic debugging and delimit_quickstart for first-run discovery. This is the clearest possible routing guidance — an agent knows exactly when to pick this tool and when to pick a sibling.

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