OnPage.dev

Site memory

site_memory

A memory per site that every OnPage.dev tool writes to, across chats and clients. Open it first when working on a site over time. Pick with mode: open = Open or create the memory, bind it to this chat, get the brief and next steps (default). Needs url. next = The best next steps from everything recorded. timeline = What happened, newest first. note = Record a decision or context. Needs note. forget = Delete the memory (ask the user first). Needs memory_key.

Input Schema

Name	Required	Description
`url`	No	The site's home page.
`kind`	No
`mode`	No	Default open.
`note`	No
`limit`	No
`detail`	No	brief = short summary.
`memory_key`	No	The memory_key you got when the memory was created.
`share_learning`	No	Opt in (true) or out (false) of sharing anonymous results: only the fix type and the rounded lift, never the site, URLs or numbers.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 14, 2026

removedOutput schema / description

Removed value: -"The result as structured data; fields depend on mode."

Changed1 schema field changedOct 13, 2026

changedInput schema / properties / detail / description

Previous value: -"brief returns a short summary, default full."New value: +"brief = short summary."

Changed1 schema field changedOct 12, 2026

addedInput schema / properties / detail

Added value: +{
+  "description": "brief returns a short summary, default full.",
+  "enum": [
+    "full",
+    "brief"
+  ],
+  "type": "string"
+}

Changed1 schema field changedOct 12, 2026

addedInput schema / properties / share_learning

Added value: +{
+  "description": "Opt in (true) or out (false) of sharing anonymous results: only the fix type and the rounded lift, never the site, URLs or numbers.",
+  "type": "boolean"
+}

AddedOct 12, 2026

TDQS

A3.7/5.0

Behavior1/5

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

The description states that forget mode deletes the memory, which is a destructive operation, but the annotations declare destructiveHint=false. This directly contradicts the tool's own behavioral description. Even though other modes are well explained, the contradiction is serious enough to cap this dimension at 1.

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 front-loaded with purpose and usage, then compactly enumerates each mode with its behavior and required inputs. Every clause earns its place despite covering five modes, and there is no filler.

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

Completeness3/5

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

For a complex eight-parameter, multi-mode tool, the description covers the main modes and their required inputs well, and an output schema exists so return values need not be explained. However, it omits meaning for kind, limit, detail, and share_learning, and the destructiveHint contradiction leaves the agent with an inconsistent behavioral picture.

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?

The description adds conditional requirements for url, note, and memory_key, and clarifies the default mode. However, it does not explain the kind, limit, detail, or share_learning parameters, and schema description coverage is only moderate. It adds useful mode-linked semantics but leaves several parameters unaddressed.

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 clearly defines the tool as a site-specific memory that every OnPage.dev tool writes to, distinguishing it from all sibling tools. The multi-mode behavior is stated up front, so an agent immediately understands this is the central persistent memory layer for a site.

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 to open it first when working on a site over time, then explains when to use each mode: open for setup and brief, next for next steps, timeline for history, note for recording context, and forget for deletion. Required parameters per mode and the instruction to ask the user before forgetting are also included.

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

All OnPage.dev tools Inspect

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.