zscaler-mcp-server

Official

Overview Schema Source Related Servers Discussions Admin

zpa_get_lss_log_format

Read-only

Retrieve pre-built LSS log format templates (CSV, JSON, or TSV) for a specified log type, enabling quick configuration of Zscaler log streaming outputs.

Instructions

Get the pre-built LSS log-format templates (csv/json/tsv) for a log type (read-only).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`log_type`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`kind`	Yes	Catalog kind (e.g. log_types, log_format, status_codes).
`items`	Yes	The catalog payload as returned by ZPA.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.15.3Aug 19, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- addedInput schema / properties / log_type / title
```
Added value: +"Log Type"
```
- addedInput schema / title
```
Added value: +"zpa_get_lss_log_formatArguments"
```

Changed12 schema fields changedv0.14.0Jul 28, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

removedInput schema / properties / log_type / description

Removed value: -"Human-readable LSS log type (e.g. `user_activity`, `audit_logs`, `app_connector_metrics`). Use `zpa_list_lss_log_types` to discover the valid values."

removedInput schema / properties / log_type / title
```
Removed value: -"Log Type"
```

removedInput schema / properties / service

Removed value: -{
-  "default": "zpa",
-  "description": "The service to use.",
-  "title": "Service",
-  "type": "string"
-}

removedInput schema / title

Removed value: -"zpa_get_lss_log_formatArguments"

addedOutput schema / additionalProperties
```
Added value: +true
```

addedOutput schema / description

Added value: +"Generic catalog wrapper — keeps the SDK payload intact under `items`.\n\nThe LSS metadata endpoints return free-form dicts/lists (log types, format\ntemplates, status codes, client types). We pass them through under a single\ncurated container rather than inventing per-catalog schemas."

addedOutput schema / properties / items

Added value: +{
+  "description": "The catalog payload as returned by ZPA.",
+  "title": "Items"
+}

addedOutput schema / properties / kind

Added value: +{
+  "description": "Catalog kind (e.g. log_types, log_format, status_codes).",
+  "title": "Kind",
+  "type": "string"
+}

removedOutput schema / properties / result

Removed value: -{
-  "additionalProperties": true,
-  "title": "Result",
-  "type": "object"
-}

changedOutput schema / required

Previous value: -[
-  "result"
-]New value: +[
+  "kind",
+  "items"
+]

changedOutput schema / title

Previous value: -"zpa_get_lss_log_formatOutput"New value: +"Catalog"

First observedv0.12.7Jun 24, 2026

TDQS

A3.6/5.0

Behavior3/5

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

The read-only nature is declared in annotations and repeated in the description. The description adds useful context that the result is a pre-built template in csv/json/tsv rather than a computed or mutable resource. It does not, however, describe invalid log-type behavior or explain anything about template availability per log type.

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?

Single sentence, tightly worded, and front-loaded with the core action and resource type. There is no filler or redundant restating beyond the useful '(read-only)' clarification.

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?

Given the tool has only one parameter and an output schema, the description is mostly sufficient for a straightforward read-only template fetch. However, the missing guidance on valid log_type values prevents the description from being fully self-contained for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The sole parameter log_type has no schema description and no enum values (0% coverage). The description only weakly says the tool is 'for a log type,' but does not tell the agent what valid log_type values are or point to a companion tool like zpa_list_lss_log_types. This is a meaningful gap for reliable invocation.

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?

Description uses a specific verb ('Get') and identifies the exact resource ('pre-built LSS log-format templates') with format variants (csv/json/tsv) and a clear scoping dimension ('for a log type'). This clearly distinguishes it from sibling tools like zpa_get_lss_config or zpa_list_lss_log_types.

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 its usage context: retrieve a static format template for a specific log type. However, it does not explicitly say when to prefer this over related LSS tools, nor does it mention any prerequisites or alternative approaches such as using zpa_list_lss_log_types to discover valid log types.

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

Deploy Server