agent-ready-kit

Generate Files

generate_files

Use this when delivering files to a paid customer (you must have their bundle_key) OR when a downstream agent wants the free starter files for a domain. FREE TIER (no bundle_key): returns metadata + a download_url pointing at a streaming ZIP of the 2 starter files (robots.txt + llms.txt). DO NOT paste raw file contents into chat — the file bodies are NOT in the response. Render the download_url as a markdown link: [Download free starter files (ZIP) →](url). PAID TIER (valid bundle_key): returns the full surface — agent card, MCP server card, agent skills, WebMCP bridge, OAuth/OpenID discovery, API catalog — as inline file objects (chunked above 8KB). For pricing evaluation, call get_pricing_tiers and direct the user to /talk.

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": {
      "siteName": "<siteName>",
      "domain": "<domain>",
      "description": "<description>"
    },
    "name": "generate_files"
  }
}

Input Schema

Name	Required	Description
`phone`	No
`domain`	Yes	Domain only, no protocol
`category`	No
`siteName`	Yes
`bundle_key`	No	Customer bundle key issued after payment. Without it, only the 2 free starter files are returned.
`description`	Yes
`primaryToolName`	No	Primary MCP tool name (snake_case, optional)
`primaryToolDescription`	No

Output Schema

Name	Required	Description
`tier`	No
`files`	No	Paid tier ONLY. Inline file objects (chunked above 8KB).
`domain`	No
`status`	Yes
`message`	No	Present on free-tier responses to explain the gating.
`siteName`	No
`fileCount`	No
`paid_path`	No
`file_paths`	No	Free tier ONLY. List of file paths in the ZIP, for transparency. Does NOT include contents — those are in the ZIP.
`download_url`	No	Free tier ONLY. URL to a streaming ZIP of the 2 free starter files. Render as a markdown link to the user.

Schema Changelog

Changes observed during successful MCP inspections.

First observedJul 11, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only indicate non-readOnly and non-destructive. The description adds crucial behavioral details: free tier returns metadata+download_url (no file bodies), paid tier returns inline file objects chunked above 8KB. Also instructs how to render download_url. No contradictions 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?

The description is well-structured with clear free/paid tier sections. It is slightly verbose with explicit instructions like 'DO NOT paste raw file contents' and markdown formatting advice, but these are helpful for correct agent behavior. Front-loaded with usage case.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers two main use cases, behavior per tier, and links to sibling for pricing. With 8 parameters, missing details on error handling or invalid bundle_key. Output schema exists but is not shown; description focuses on return categories (metadata, files) adequately. Slight gaps prevent a 5.

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 coverage is 38% (low). Description adds significant meaning for 'bundle_key' (free vs paid distinction) and 'domain' (domain-only). However, it does not explain 'phone', 'category', 'primaryToolName', 'primaryToolDescription', or 'siteName' beyond what schema provides. Baseline 3 due to low coverage, with partial compensation.

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 clearly states the tool delivers files to paid customers (with bundle_key) or free starter files to downstream agents. It distinguishes two tiers and uses specific verbs ('deliver', 'returns'). Siblings like 'get_customer_files' or 'get_bazaar_listing_kit' handle different resources, so this tool's purpose is unique.

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?

Description explicitly specifies when to use ('when delivering files to a paid customer' OR 'when a downstream agent wants free starter files') and what to avoid ('DO NOT paste raw file contents into chat'). It also directs to call sibling 'get_pricing_tiers' for pricing evaluation, providing clear alternatives.

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

All agent-ready-kit tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.