query_clickhouse

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

With no annotations, the description carries full burden. It discloses the read-only nature, allowed statement types (SELECT, SHOW, DESCRIBE, EXPLAIN), and the 500-row cap. This transparently sets expectations about safe usage and limits.

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

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

The description is front-loaded with the core purpose, followed by constraints and use cases. Every sentence serves a purpose: allowed statements, row cap, telemetry use cases, parameter description, and examples. No wasted words.

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

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

With one parameter and an output schema (not shown but present), the description covers purpose, constraints, use cases, and parameter semantics. It does not need to explain return values thanks to the output schema. It is sufficiently complete 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.

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

Schema coverage is 0%, so the description must compensate. It defines sql as "A read-only SQL statement" and provides three concrete examples showing valid query forms, which gives the agent clear guidance beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource: "Run a read-only SQL query against ClickHouse (telemetry data)." It clearly distinguishes from sibling tools by being the general ad-hoc SQL interface, while siblings like ch_list_tables and ch_sample_data cover specific narrower operations.

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

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

It gives clear use cases: "Use this for product telemetry: active instances, version distribution, storage engines, deployment types, CPU architecture, cluster metrics." It does not explicitly contrast with alternatives (e.g., when to use ch_list_tables instead), but the context makes those alternatives obvious.

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