Skip to main content
Glama
Sign In

Convika

by com.convika
OverviewDiscussionsAdmin

Update custom domain settings

update_domain_settings
Idempotent

Use this tool when the user wants to stop or allow AI bots on their custom domain (独自ドメイン), such as "ChatGPT に読ませたくない", "AI の学習に使わせない", or "allow Perplexity again".

Turns a custom domain's AI-bot switches on or off, for all of this workspace's pages on that domain. Convika writes the change into the domain's robots.txt within about a minute; nothing on the pages changes. Each bot re-reads robots.txt on its own schedule (OpenAI says about 24 hours), so don't promise the user an immediate stop.

  • allowAiAnswerBots: OAI-SearchBot, Claude-SearchBot, PerplexityBot, DuckAssistBot, ChatGPT-User, Claude-User, Perplexity-User. Off, AI search and answers stop reading the site, so it may stop appearing in their answers.

  • allowAiTrainingBots: GPTBot, ClaudeBot, CCBot, Bytespider, Google-Extended, Applebot-Extended. Off asks them not to use the pages for training. Google-Extended doesn't affect Google Search. Tell the user, before and after:

  • The fetchers that open a page because a person asked (ChatGPT-User, Claude-User, Perplexity-User) may ignore robots.txt.

  • Googlebot and Bingbot can't be switched off: Google's AI Overviews read pages as Googlebot. To keep a page out of search results, publish it as a Private link (Pro) on the dashboard (「限定公開」 in Japanese); Free pages are public.

  • robots.txt is a request that well-behaved bots follow, not a block. Applies only to this workspace's pages on the domain. Free and paid plans alike. Call get_domain first if you don't know the domain's id or hostname. Change it only when the user asks.

Input Schema

NameRequiredDescriptionDefault
domainYesThe domain's id or hostname, such as www.example.com
allowAiAnswerBotsNotrue allows AI search and answer bots, false disallows them in robots.txt
allowAiTrainingBotsNotrue allows AI training bots, false disallows them in robots.txt

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A5/5.0
Behavior5/5

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

The description adds substantial context beyond the annotations: Convika writes robots.txt within about a minute, pages themselves do not change, bots re-read on their own schedules (OpenAI about 24 hours), and users should not be promised an immediate stop. It also explains which bots are affected, caveats about fetchers and Googlebot/Bingbot, and that robots.txt is a request rather than a block.

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 long but well structured: it front-loads the usage scenario, then explains the behavioral effect, then gives bot-specific details and user-facing warnings in bullets. Given the operational caveats and user communication requirements, every section serves a purpose.

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 mutation tool with no output schema, the description covers what is modified, timing, propagation, affected bots, limitations, prerequisites, and user messaging. An agent has enough information to invoke it correctly and set appropriate expectations.

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

Parameters5/5

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

Although the schema coverage is already 100%, the description meaningfully expands the boolean parameters by naming the exact bots controlled by allowAiAnswerBots and allowAiTrainingBots and explaining the consequences of turning them off. It also clarifies that the domain parameter applies only to this workspace's pages on that domain.

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 states a specific verb and resource: turning a custom domain's AI-bot switches on or off in robots.txt. It clearly distinguishes this mutation tool from read-oriented siblings like get_domain and get_ai_access by explaining exactly what it changes and what it does not change.

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?

It explicitly says when to use the tool, including example user intents in English and Japanese, and states that get_domain should be called first if the domain id or hostname is unknown. It also includes a clear restriction: change it only when the user asks.

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

All Convika toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources