Skip to main content
Glama

agent-ready-kit

by com.mudko

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
phoneNo
domainYesDomain only, no protocol
categoryNo
siteNameYes
bundle_keyNoCustomer bundle key issued after payment. Without it, only the 2 free starter files are returned.
descriptionYes
primaryToolNameNoPrimary MCP tool name (snake_case, optional)
primaryToolDescriptionNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
tierNo
filesNoPaid tier ONLY. Inline file objects (chunked above 8KB).
domainNo
statusYes
messageNoPresent on free-tier responses to explain the gating.
siteNameNo
fileCountNo
paid_pathNo
file_pathsNoFree tier ONLY. List of file paths in the ZIP, for transparency. Does NOT include contents — those are in the ZIP.
download_urlNoFree tier ONLY. URL to a streaming ZIP of the 2 free starter files. Render as a markdown link to the user.

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 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose, with descriptions that prevent confusion. Tools like scan_site and run_site_audit are differentiated by their focus on AI-readiness vs. site quality.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case, with clear action words like 'scan', 'create', 'get', 'verify'. Even longer names like 'summarize_scan_for_humans' maintain consistency.

Tool Count4/5

22 tools is slightly above the ideal range but justified by the comprehensive scope of the server, covering scanning, analysis, quoting, file delivery, and verification. Some tools like generate_files and get_customer_files could overlap but serve different contexts.

Completeness5/5

The tool surface covers the entire workflow from site scanning to deployment verification, with no obvious dead ends. All necessary operations for making a site agent-ready are present, including edge cases like x402 validation and credential verification.

Resources