Kafka MCP

Overview Schema Source Related Servers Discussions Admin

describe_topic

Describe up to 500 Kafka topics in one call: retrieve partition offsets, message counts, disk size, timestamps, and effective config, with missing topics reported per item.

Instructions

Describe 1 to 500 topics in one call through items: partitions, offset ranges, approximate message count, size on disk (size_bytes per partition and topic, replicated_size_bytes across replicas), oldest/newest timestamps and complete effective configuration. Config entries identify whether values are inherited or topic-specific.

Results follow items order, each carrying index with result or error, so a topic that does not exist is reported against its own item rather than failing the call. Describing one topic is an items array of length one.

Message counts are offset spans and may overcount after retention or compaction.

Input Schema

Name	Required	Description	Default
`items`	Yes	The topics to describe, 1 to 500 of them. Describing one topic is an array of length one. Results follow this order and a missing topic is reported against its own item.

Output Schema

Name	Required	Description	Default
`atomic`	Yes
`failed`	Yes
`applied`	Yes
`results`	Yes
`succeeded`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.2.7Oct 25, 2026

changedInput schema / properties / items / description

Previous value: -"The topics to describe, 1 to 20 of them. Describing one topic is an array of length one. Results follow this order and a missing topic is reported against its own item."New value: +"The topics to describe, 1 to 500 of them. Describing one topic is an array of length one. Results follow this order and a missing topic is reported against its own item."

addedOutput schema / properties / results / items / properties / result / properties / partitions / items / properties / size_bytes
```
Added value: +{
+  "type": [
+    "null",
+    "integer"
+  ]
+}
```
addedOutput schema / properties / results / items / properties / result / properties / replicated_size_bytes
```
Added value: +{
+  "type": [
+    "null",
+    "integer"
+  ]
+}
```
addedOutput schema / properties / results / items / properties / result / properties / size_bytes
```
Added value: +{
+  "type": [
+    "null",
+    "integer"
+  ]
+}
```

addedOutput schema / properties / results / items / properties / result / properties / warnings

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": [
+    "null",
+    "array"
+  ]
+}

First observedv0.2.0Oct 7, 2026

TDQS

A3.7/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses per-item error isolation (a missing topic is reported against its own item instead of failing the call), result ordering by items index, and the important caveat that message counts are offset spans that may overcount after retention or compaction. It stops short of stating that the operation is read-only or of any permission/auth requirements.

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 core action and scope in the first clause, then layered detail on return contents and caveats. The return-field enumeration (size_bytes, replicated_size_bytes, inherited vs topic-specific config) is dense but each item earns its place by disambiguating the payload.

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?

An output schema exists, so return values need not be explained, yet the description adds genuinely useful semantics (offset-span overcounting, config inheritance) that a schema alone would not convey. For a single-parameter read tool, the only real omission is an explicit statement that the call is non-mutating.

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 coverage is 100% at one parameter, so the schema already documents `items` and exact/case-sensitive topic matching. The description restates the 1-to-500 bound, the single-topic-is-length-one convention and the error-isolation behavior, which mostly duplicates the schema's own items description rather than adding new semantics.

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 ('Describe ... topics') plus the batching scope (1 to 500) and enumerates exactly what is returned: partitions, offsets, sizes, timestamps, effective config. It is clearly distinguishable from mutation siblings, but it never names list_topics or explains how 'describe' differs from 'list', leaving that inference to the agent.

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?

Usage is implied rather than stated: the batching range and the note that 'describing one topic is an items array of length one' tell the agent how to call it, but there is no explicit guidance on when to reach for describe_topic over list_topics or when to split into multiple calls.

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