Skip to main content
Glama

OnPage.dev

by dev.onpage
OverviewDiscussionsAdmin

llms.txt

llms_txt
Read-onlyIdempotent

The llms.txt file for AI assistants. Pick with mode: generate = Write one from the sitemap and home page. Needs url. validate = Check an existing one and its links. Needs url.

Input Schema

NameRequiredDescriptionDefault
urlNoHome page of the site, for example https://example.com.
modeNoDefault generate.
textNoOptional llms.txt content to validate instead of the live file.
detailNobrief = short summary.
memory_keyNosite_memory key, records this call.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedOutput schema / description
      Removed value: -"The result as structured data; fields depend on mode."
  2. Changed2 schema fields changed
    • changedInput schema / properties / detail / description
      Previous value: -"brief returns a short summary, default full."New value: +"brief = short summary."
    • changedInput schema / properties / memory_key / description
      Previous value: -"Optional site_memory key, to record this call in the site memory."New value: +"site_memory key, records this call."
  3. Changed1 schema field changed
    • addedInput schema / properties / detail
      Added value: +{
+  "description": "brief returns a short summary, default full.",
+  "enum": [
+    "full",
+    "brief"
+  ],
+  "type": "string"
+}
  4. Changed1 schema field changed
    • addedInput schema / properties / memory_key
      Added value: +{
+  "description": "Optional site_memory key, to record this call in the site memory.",
+  "maxLength": 80,
+  "type": "string"
+}
  5. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations carry the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the bar is lower. The description usefully states that generate derives content from the sitemap and home page and that validate inspects links, but says nothing about network access, rate limits, or that memory_key causes the call to be recorded.

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?

Three terse sentences, front-loaded with the resource and then the mode decision. Every clause carries information; nothing is padded or restated.

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?

For a 5-parameter tool with full schema coverage plus an output schema, the description covers the decision an agent must make (which mode, and that a URL is needed) and correctly leaves return values to the output schema. The incomplete handling of the text/detail/memory_key path is a minor gap.

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; the description exceeds it by supplying the conditional requirement the schema does not encode ('Needs url' for both modes) even though no parameter is marked required. It is slightly imprecise, since url may be unnecessary when text is supplied, and it never mentions text, detail, or memory_key.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names the resource (the llms.txt file for AI assistants) and splits it into two concrete operations with explicit verbs: generate writes one from the sitemap and home page, validate checks an existing one and its links. It does not, however, distinguish itself from adjacent siblings such as robots_txt or sitemap, which an agent could plausibly confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Pick with mode' framing gives a clear branch rule, and each mode's precondition ('Needs url') tells the agent what must be supplied before calling. No exclusions or alternative-tool routing are given, so it stops short of a 5.

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

All OnPage.dev toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources