Lianex — Australian price comparison

The published product-permalink index

lianex_products

Read-onlyIdempotent

List published product permalink IDs and their updated_at freshness. Use the IDs to request individual products. Over HTTP, omitting limit returns the full published index, while the MCP tool lianex_products returns one page of 50; otherwise offset, page_size and has_more describe the page. ignored lists unusable paging parameters. Results can change between requests. Cache-only.

Input Schema

Name	Required	Description	Default
`limit`	No	How many permalinks to return, clamped to 50. Over HTTP, omitting it returns the whole index (the sitemap's own source, never truncated by default). The MCP tool lianex_products returns 50 per call when it is omitted; continue with offset while has_more is true.
`offset`	No	How many permalinks to skip. Unusable values are ignored and named in `ignored`; a negative value is clamped to 0.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedNov 2, 2026
- removedOutput schema / $defs / ProductIndexEntry / properties / id / description
```
Removed value: -"The permalink id — its page is `https://lianex.ai/p/<id>`."
```
- removedOutput schema / $defs / ProductIndexEntry / properties / id / title
```
Removed value: -"Id"
```
- removedOutput schema / $defs / ProductIndexEntry / properties / updated_at / description
```
Removed value: -"ISO-8601 freshness, or `null`."
```
- removedOutput schema / $defs / ProductIndexEntry / properties / updated_at / title
```
Removed value: -"Updated At"
```
- removedOutput schema / $defs / ProductIndexEntry / title
```
Removed value: -"ProductIndexEntry"
```
- removedOutput schema / $defs / ProductIndexResponse / description
```
Removed value: -"Published product permalink IDs. Omit limit to return the full index; page_size is then null."
```
- removedOutput schema / $defs / ProductIndexResponse / properties / has_more / description
```
Removed value: -"Whether another page follows in the current result set."
```
- removedOutput schema / $defs / ProductIndexResponse / properties / has_more / title
```
Removed value: -"Has More"
```
- removedOutput schema / $defs / ProductIndexResponse / properties / ignored / description
```
Removed value: -"Names of paging parameters we could not use. A bad value is ignored, never refused."
```
- removedOutput schema / $defs / ProductIndexResponse / properties / ignored / title
```
Removed value: -"Ignored"
```
- removedOutput schema / $defs / ProductIndexResponse / properties / offset / description
```
Removed value: -"The offset actually applied (a negative request is clamped to 0)."
```
- removedOutput schema / $defs / ProductIndexResponse / properties / offset / title
```
Removed value: -"Offset"
```
- removedOutput schema / $defs / ProductIndexResponse / properties / page_size / description
```
Removed value: -"The page size actually applied, or `null` when the whole index was returned."
```
- removedOutput schema / $defs / ProductIndexResponse / properties / page_size / title
```
Removed value: -"Page Size"
```
- removedOutput schema / $defs / ProductIndexResponse / properties / products / title
```
Removed value: -"Products"
```
- removedOutput schema / $defs / ProductIndexResponse / title
```
Removed value: -"ProductIndexResponse"
```
- removedOutput schema / title
```
Removed value: -"Response Public Products Api Public Products Get"
```

Changed7 schema fields changedOct 29, 2026

addedInput schema / properties / limit / anyOf

Added value: +[
+  {
+    "type": "integer"
+  },
+  {
+    "pattern": "^-?[0-9]+$",
+    "type": "string"
+  }
+]

changedInput schema / properties / limit / default
```
Previous value: -""New value: +50
```

changedInput schema / properties / limit / description

Previous value: -"How many permalinks to return, clamped to 50. OMIT IT and you get the whole index — this is the sitemap's own source, so it is never truncated by default."New value: +"How many permalinks to return, clamped to 50. Over HTTP, omitting it returns the whole index (the sitemap's own source, never truncated by default). The MCP tool lianex_products returns 50 per call when it is omitted; continue with offset while has_more is true."

removedInput schema / properties / limit / type
```
Removed value: -"string"
```

addedInput schema / properties / offset / anyOf

Added value: +[
+  {
+    "type": "integer"
+  },
+  {
+    "pattern": "^-?[0-9]+$",
+    "type": "string"
+  }
+]

removedInput schema / properties / offset / default
```
Removed value: -""
```
removedInput schema / properties / offset / type
```
Removed value: -"string"
```

First observedOct 22, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already cover read-only/idempotent/no-destruction, and the description adds real substance on top: cache-only sourcing, results that can change between requests, hard clamping to 50, and an `ignored` field naming unusable paging parameters. The only gap is why the HTTP and MCP behaviors differ so sharply, which matters for an agent reasoning about completeness of the index.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the verb and resource, then paging semantics, then the cache caveat. Dense but every clause carries information. Minor cost: 'page_size and has_more describe the page' mixes response fields into a sentence about paging parameters, adding a small parsing burden.

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?

With an output schema present and annotations covering safety, the description need only cover paging and staleness, which it does thoroughly. It stops short of explaining how a permalink ID relates to the safe_id/slug used by sibling tools, leaving the agent to infer the handoff.

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?

Schema coverage is 100%, yet the description still adds critical meaning the schema does not surface on its own: omitting `limit` yields the entire index over HTTP but only a 50-item page via MCP, and invalid values surface in `ignored`. That directly changes how an agent should page.

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?

States a specific verb and resource: 'List published product permalink IDs and their updated_at freshness,' plus the follow-on action ('use the IDs to request individual products'). It is clearly an index/enumeration tool, distinguishable from browse/search siblings, though it never names a specific sibling by name.

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?

It implies a two-step workflow (list IDs, then request individual products) and gives paging continuation advice ('continue with offset while has_more is true'), but it never states when to prefer this over lianex_browse, lianex_search, or lianex_browse_by_slug. Usage is implied rather than delimited.

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

All Lianex — Australian price comparison 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?