Skip to main content
Glama

Delimit Project Config

delimit_project_config

Load, initialize, or query delimit.yml to manage project AI configuration. Use init to create config with governance mode and policy preset; use model to find task-specific settings.

Instructions

Manage delimit.yml project configuration (load / init / model).

When to use: to inspect, create, or query the project's delimit.yml AI configuration. When NOT to use: for governance state (use delimit_gov_status) or to manage prompts (use delimit_playbook).

Sibling contrast: delimit_gov_status reports governance runtime state; this manages the static config file.

Side effects: action="init" writes a new delimit.yml at project_path via ai.project_config.init_project_config. "load" and "model" are read-only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoGovernance mode (only for init). One of "advisory", "guarded", "enforce". Default "advisory".advisory
actionNo"load" (default), "init", or "model".load
presetNoPolicy preset (only for init). One of "strict", "default", "relaxed". Default "default".default
task_typeNoTask type for model lookup (only for action="model").
project_pathNoProject root directory. Default "." (cwd)..

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed5 schema fields changedv4.7.9
    • changedInput schema / properties / action / description
      Previous value: -"\"load\", \"init\", or \"model\"."New value: +"\"load\" (default), \"init\", or \"model\"."
    • changedInput schema / properties / mode / description
      Previous value: -"Governance mode for init (advisory/guarded/enforce)."New value: +"Governance mode (only for init). One of \"advisory\", \"guarded\", \"enforce\". Default \"advisory\"."
    • changedInput schema / properties / preset / description
      Previous value: -"Policy preset for init (strict/default/relaxed)."New value: +"Policy preset (only for init). One of \"strict\", \"default\", \"relaxed\". Default \"default\"."
    • changedInput schema / properties / project_path / description
      Previous value: -"Project root directory."New value: +"Project root directory. Default \".\" (cwd)."
    • changedInput schema / properties / task_type / description
      Previous value: -"Task type for model lookup (refactoring/testing/docs/debugging)."New value: +"Task type for model lookup (only for action=\"model\")."
  2. Addedv4.5.5

TDQS

A4.7/5.0
Behavior5/5

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

The description discloses concrete side effects: action='init' writes a new delimit.yml at project_path, while 'load' and 'model' are read-only. This goes beyond the annotations and clarifies the mixed read/write nature of the tool, which is essential for safe invocation.

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 sections, front-loads the core purpose, and every sentence adds useful guidance. It is compact despite covering usage, exclusions, sibling contrast, and side effects.

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?

Given the tool's multi-action nature and conditional parameters, the description provides complete context: what the tool manages, when to use it, when not to, how it differs from the closest sibling, and what side effects to expect. An output schema exists, so return-value documentation is not required here.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds minimal value beyond the schema: it confirms that 'init' writes to project_path and lists the modes, but the schema already documents parameter-specific constraints like 'only for init' and 'only for action=model'.

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 and resource: 'Manage delimit.yml project configuration (load / init / model).' It names the exact file and modes of operation, and the sibling contrast explicitly distinguishes it from delimit_gov_status, so an agent can tell them apart.

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 provides explicit 'When to use' and 'When NOT to use' guidance, naming delimit_gov_status and delimit_playbook as alternatives for governance state and prompt management. This fully routes the agent to the correct tool.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/delimit-ai/delimit-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server