Skip to main content
Glama

Create blueprint

create_blueprint

Save a new blueprint (an AI agent instruction file such as AGENTS.md or CLAUDE.md) to the token user's LynxPrompt account. Each call creates a new blueprint, even with the same name; to change an existing one use update_blueprint.

Instructions

Save a new blueprint (an AI agent instruction file such as AGENTS.md or CLAUDE.md) to the token user's LynxPrompt account. Each call creates a new blueprint, even with the same name; to change an existing one use update_blueprint. Private by default; visibility PUBLIC publishes it to the public marketplace. To place it in a monorepo hierarchy pass hierarchy_id and repository_path. Returns the new blueprint with its bp_ id.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "content": "<content>"
    },
    "name": "create_blueprint"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesBlueprint name, at least 3 characters, e.g. "Next.js app AGENTS.md".
tagsNoUp to 10 tags of at most 30 characters, e.g. ["react", "typescript"].
typeNoFile format the blueprint is for. AGENTS_MD is AGENTS.md, CLAUDE_MD is CLAUDE.md, CURSOR_MDC a .cursor/rules/*.mdc file, *_COMMAND a slash command, AGENT_SKILL a skill's SKILL.md, AGENT_DEFINITION a subagent such as .claude/agents/<name>.md, MCP_CONFIG an .mcp.json, CUSTOM anything else.
contentYesThe full text of the instruction file, at least 10 characters.
team_idNoTeam to share a TEAM blueprint with; send it together with visibility TEAM. Needed only when you belong to more than one team; with one team, that team is used.
categoryNoCategory slug, e.g. web, devops, saas, mobile, data or other.
parent_idNoParent blueprint inside the hierarchy (bp_...), e.g. the root AGENTS.md of the repo.
visibilityNoPRIVATE (only you), TEAM (your team) or PUBLIC. PUBLIC publishes the content to the public marketplace where anyone can read it.
descriptionNoOne or two sentences on what the blueprint is for.
hierarchy_idNoHierarchy to add the blueprint to (ha_..., from list_hierarchies or create_hierarchy).
repository_pathNoWhere the file lives in the repository, relative to its root, e.g. packages/api/AGENTS.md.

Output Schema

NameRequiredDescriptionDefault
successNo
blueprintNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed20 schema fields changedv0.3.0
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / category
      Added value: +{
      +  "description": "Category slug, e.g. web, devops, saas, mobile, data or other.",
      +  "maxLength": 50,
      +  "type": "string"
      +}
    • changedInput schema / properties / content / description
      Previous value: -"Blueprint content (the actual prompt/instructions text)"New value: +"The full text of the instruction file, at least 10 characters."
    • addedInput schema / properties / content / minLength
      Added value: +10
    • changedInput schema / properties / description / description
      Previous value: -"Short description of the blueprint (optional)"New value: +"One or two sentences on what the blueprint is for."
    • addedInput schema / properties / description / maxLength
      Added value: +1000
    • addedInput schema / properties / hierarchy_id
      Added value: +{
      +  "description": "Hierarchy to add the blueprint to (ha_..., from list_hierarchies or create_hierarchy).",
      +  "pattern": "^[A-Za-z0-9][A-Za-z0-9_-]{0,127}$",
      +  "type": "string"
      +}
    • changedInput schema / properties / name / description
      Previous value: -"Name of the blueprint"New value: +"Blueprint name, at least 3 characters, e.g. \"Next.js app AGENTS.md\"."
    • addedInput schema / properties / name / maxLength
      Added value: +200
    • addedInput schema / properties / name / minLength
      Added value: +3
    • addedInput schema / properties / parent_id
      Added value: +{
      +  "description": "Parent blueprint inside the hierarchy (bp_...), e.g. the root AGENTS.md of the repo.",
      +  "pattern": "^[A-Za-z0-9][A-Za-z0-9_-]{0,127}$",
      +  "type": "string"
      +}
    • addedInput schema / properties / repository_path
      Added value: +{
      +  "description": "Where the file lives in the repository, relative to its root, e.g. packages/api/AGENTS.md.",
      +  "maxLength": 500,
      +  "type": "string"
      +}
    • addedInput schema / properties / tags
      Added value: +{
      +  "description": "Up to 10 tags of at most 30 characters, e.g. [\"react\", \"typescript\"].",
      +  "items": {
      +    "maxLength": 30,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "maxItems": 10,
      +  "type": "array"
      +}
    • addedInput schema / properties / team_id
      Added value: +{
      +  "description": "Team to share a TEAM blueprint with; send it together with visibility TEAM. Needed only when you belong to more than one team; with one team, that team is used.",
      +  "pattern": "^[A-Za-z0-9][A-Za-z0-9_-]{0,127}$",
      +  "type": "string"
      +}
    • changedInput schema / properties / type / description
      Previous value: -"Blueprint type, e.g. AGENTS_MD, CLAUDE_MD"New value: +"File format the blueprint is for. AGENTS_MD is AGENTS.md, CLAUDE_MD is CLAUDE.md, CURSOR_MDC a .cursor/rules/*.mdc file, *_COMMAND a slash command, AGENT_SKILL a skill's SKILL.md, AGENT_DEFINITION a subagent such as .claude/agents/<name>.md, MCP_CONFIG an .mcp.json, CUSTOM anything else."
    • addedInput schema / properties / type / enum
      Added value: +[
      +  "AGENTS_MD",
      +  "CLAUDE_MD",
      +  "COPILOT_INSTRUCTIONS",
      +  "WINDSURF_RULES",
      +  "CLINE_RULES",
      +  "CODEX_MD",
      +  "CURSOR_RULES",
      +  "CURSOR_MDC",
      +  "GEMINI_MD",
      +  "ZED_INSTRUCTIONS",
      +  "VOID_CONFIG",
      +  "TRAE_RULES",
      +  "IDX_CONFIG",
      +  "ROO_RULES",
      +  "CONTINUE_CONFIG",
      +  "CODY_CONFIG",
      +  "TABNINE_CONFIG",
      +  "AMAZONQ_RULES",
      +  "AUGMENT_RULES",
      +  "KILOCODE_RULES",
      +  "JUNIE_GUIDELINES",
      +  "KIRO_STEERING",
      +  "AIDER_MD",
      +  "GOOSEHINTS",
      +  "WARP_MD",
      +  "OPENCODE_JSON",
      +  "OPENHANDS_MD",
      +  "CURSOR_COMMAND",
      +  "CLAUDE_COMMAND",
      +  "WINDSURF_WORKFLOW",
      +  "COPILOT_PROMPT",
      +  "CONTINUE_PROMPT",
      +  "OPENCODE_COMMAND",
      +  "AGENT_SKILL",
      +  "MCP_CONFIG",
      +  "AGENT_DEFINITION",
      +  "CUSTOM"
      +]
    • changedInput schema / properties / visibility / description
      Previous value: -"Visibility: PRIVATE, TEAM, or PUBLIC (optional, defaults to PRIVATE)"New value: +"PRIVATE (only you), TEAM (your team) or PUBLIC. PUBLIC publishes the content to the public marketplace where anyone can read it."
    • addedInput schema / properties / visibility / enum
      Added value: +[
      +  "PRIVATE",
      +  "TEAM",
      +  "PUBLIC"
      +]
    • changedInput schema / required
      Previous value: -[
      -  "name",
      -  "content",
      -  "type"
      -]New value: +[
      +  "name",
      +  "content"
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "blueprint": {
      +      "properties": {
      +        "category": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "content": {
      +          "description": "The blueprint text (only on single-blueprint reads and updates)",
      +          "type": "string"
      +        },
      +        "content_checksum": {
      +          "description": "Pass as expected_checksum to update_blueprint",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "created_at": {
      +          "type": "string"
      +        },
      +        "description": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "hierarchy_id": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "id": {
      +          "description": "Blueprint id, e.g. bp_clx1abc",
      +          "type": "string"
      +        },
      +        "name": {
      +          "type": "string"
      +        },
      +        "parent_id": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "repository_path": {
      +          "description": "Path in the repository; only the file name for a public blueprint of someone outside your team",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "tags": {
      +          "items": {
      +            "type": "string"
      +          },
      +          "type": "array"
      +        },
      +        "tier": {
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "type": {
      +          "description": "File format, e.g. AGENTS_MD or CLAUDE_MD",
      +          "type": "string"
      +        },
      +        "updated_at": {
      +          "type": "string"
      +        },
      +        "visibility": {
      +          "description": "PRIVATE, TEAM or PUBLIC",
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "success": {
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare idempotentHint=false, but the description converts that into a concrete consequence an agent can act on (duplicate names create duplicate records). It adds defaults and side effects the annotations cannot express: private by default, PUBLIC exposes content to a public marketplace where anyone can read it, and the call returns the new blueprint with a bp_ id. No contradiction with the non-readOnly, non-destructive, openWorld annotation profile.

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?

Five tight sentences for an 11-parameter tool, front-loaded with what it does and the create-vs-update rule, then defaults, then optional hierarchy usage, then the return value. No sentence is redundant with the schema or annotations.

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 non-idempotent, open-world write tool with 11 parameters and an output schema, the description covers the decisions that actually change agent behavior: which tool to pick, what gets exposed publicly, and how the hierarchy parameters pair. Return values are delegated to the existing output schema and per-field formats to the 100%-covered schema.

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, and the description earns above that by documenting cross-parameter coupling the schema does not state: team_id must be sent together with visibility TEAM and is only needed with multiple teams, and hierarchy_id must be paired with repository_path for monorepo placement. It does not restate per-parameter formats (lengths, slug examples), correctly leaving those to 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 ("Save a new blueprint") and immediately defines the resource for anyone unfamiliar ("an AI agent instruction file such as AGENTS.md or CLAUDE.md"). It also distinguishes itself from the nearest sibling by name: "to change an existing one use update_blueprint."

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?

Explicitly states the create-vs-update decision rule ("Each call creates a new blueprint, even with the same name; to change an existing one use update_blueprint"), which is exactly the ambiguity an agent hits with create/update sibling pairs. It also gives conditional guidance for the two optional paths: visibility PUBLIC for marketplace publication and hierarchy_id + repository_path for monorepo placement.

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