generate_llms_txtDraft an llms.txt for a site from its own homepage, sitemap and page titles. Takes 10-30 seconds. The owner reviews it and publishes it at /llms.txt. Ownership management is optional and uses a separate fresh challenge.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | A domain name such as example.com (no scheme, no path). |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Input schema / properties / domain / maxLengthAdded value: +253Input schema / properties / domain / minLengthAdded value: +1Output schema / (root)Previous value: -nullNew value: +{
+ "anyOf": [
+ {
+ "additionalProperties": false,
+ "properties": {
+ "description": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "domain": {
+ "type": "string"
+ },
+ "ok": {
+ "const": true
+ },
+ "pages": {
+ "type": "integer"
+ },
+ "sampled": {
+ "type": "integer"
+ },
+ "source": {
+ "type": "string"
+ },
+ "text": {
+ "type": "string"
+ },
+ "title": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "ok",
+ "domain",
+ "title",
+ "description",
+ "pages",
+ "source",
+ "sampled",
+ "text"
+ ],
+ "type": "object"
+ },
+ {
+ "additionalProperties": true,
+ "properties": {
+ "detail": {
+ "type": "string"
+ },
+ "domain": {
+ "type": "string"
+ },
+ "error": {
+ "type": "string"
+ },
+ "hint": {
+ "type": "string"
+ },
+ "retry_after_seconds": {
+ "type": "integer"
+ }
+ },
+ "required": [
+ "error"
+ ],
+ "type": "object"
+ }
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: the 10-30 second runtime, the fact that it only drafts and a human publishes, and that ownership is handled by a separate fresh challenge.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four compact sentences that are front-loaded with the core action and immediately followed by the time cost and publish workflow. The ownership-management sentence is slightly tangential but still relevant context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, return values need no explanation, and annotations carry the safety profile. The description fills the remaining gaps (latency, draft-then-publish semantics, ownership split) adequately for a one-parameter tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single domain parameter is fully documented in the schema (format, length bounds), so the description need not repeat it. It adds nothing about the parameter beyond saying the draft is 'for a site', which is the baseline 3 case.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb (draft) and resource (llms.txt) plus the source inputs it draws on (homepage, sitemap, page titles), which distinguishes it from check_llms_txt in practice. It never names a sibling explicitly, so the differentiation is implicit rather than stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It describes the downstream workflow (owner reviews and publishes at /llms.txt) and notes ownership management is optional, which implies when this tool fits. However, it gives no explicit guidance on when to use it versus check_llms_txt, recrawl_site, or update_site.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.