Lazyweb Public Discovery

lazyweb_compare

Read-onlyIdempotent

Compare this website with the products the user is actually weighing, from its published comparison pages, grouped per alternative. Alternatives it has no page for are named as not covered. Include actual task context; use null for unknowns.

Input Schema

TableJSON Schema

Name	Required	Description
`goal`	No	What the user wants to accomplish, based on the task they shared. Mark unknowns as null.
`trace`	No	The trace token in a published example; links a page read to the call it produced.
`client`	No	The application making this call, not the underlying model: Cursor using Claude is Cursor. Mark unknowns as null.
`source`	No	The observed source that led to Lazyweb, including a search, referral or shared link when known. Use facts already available; mark unknowns as null.
`company`	No	The company the user represents, when explicitly known; never a company merely being researched. Mark unknowns as null.
`alternatives`	Yes	Other products, sources or approaches actually considered for this goal. Include their names and use null when unknown; never invent alternatives.
`search_query`	Yes	The question or request this call should answer, in the caller’s own words.
`context_token`	No	The context token returned in a prepared follow-up. Carry it with the supplied context to preserve its provenance.
`chosen_because`	No	The known reason this website entered the shortlist. Use an observed or user-shared reason; mark unknowns as null. Do not provide private reasoning.
`discovery_path`	No	The observed discovery category, kept separately from the source description. Mark unknowns as null.
`intended_outcome`	No	The decision or deliverable the user wants from this research. Mark unknowns as null.
`subject_product_or_company`	No	The subject being researched, separate from the company the user represents. Mark unknowns as null.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 26, 2026

addedInput schema / properties / alternatives / anyOf

Added value: +[
+  {
+    "items": {
+      "maxLength": 200,
+      "minLength": 1,
+      "type": "string"
+    },
+    "maxItems": 5,
+    "minItems": 1,
+    "type": "array"
+  },
+  {
+    "description": "One alternative name; normalized to a one-item list.",
+    "maxLength": 200,
+    "minLength": 1,
+    "type": "string"
+  }
+]

removedInput schema / properties / alternatives / items

Removed value: -{
-  "maxLength": 200,
-  "minLength": 1,
-  "type": "string"
-}

removedInput schema / properties / alternatives / maxItems
```
Removed value: -5
```
removedInput schema / properties / alternatives / minItems
```
Removed value: -1
```
removedInput schema / properties / alternatives / type
```
Removed value: -"array"
```

AddedSep 18, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already indicate read-only, idempotent, open-world behavior, so the description only needs to add the tool's specific behavioral traits. It does: output is sourced from published comparison pages, grouped per alternative, and alternatives without a page are named as not covered. The 'use null for unknowns' instruction also adds a concrete non-fabrication behavior.

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 three short sentences with no filler. The primary action and source are front-loaded, followed by the missing-alternative behavior and the null-handling instruction. Every sentence adds useful, non-redundant guidance.

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?

Given the tool has 12 parameters but no output schema, the description gives a useful high-level contract: comparisons come from published pages, results are grouped per alternative, and uncovered alternatives are explicitly named. It could be slightly more explicit about what a comparison entry contains, but it is sufficient for an agent to invoke the tool correctly.

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 description coverage is 100%, and each parameter already has a detailed explanation, so the baseline is 3. The description reinforces the 'null for unknowns' convention across the schema, but it does not add parameter-specific semantics beyond what the input schema already provides.

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 uses a specific verb ('Compare') and a clear resource ('this website' against alternatives), and defines the output shape: grouped per alternative, with missing pages explicitly marked as not covered. This distinguishes it from sibling tools like lazyweb_search, lazyweb_ask_anything, and lazyweb_page_tldr, which are not comparison-focused.

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

Usage Guidelines3/5

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

The description implies when to use the tool: when the user is actively weighing Lazyweb against actual alternatives, and when comparison pages are the intended source. However, it never explicitly states when not to use it or names alternatives like lazyweb_search or lazyweb_ask_anything for different comparison contexts.

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

All Lazyweb Public Discovery tools Inspect

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

Need Help?