Run a read-only query

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

There are no annotations, so the description carries the full burden. It discloses the read-only safety posture, states that non-read statements will be refused, and notes the CLICKHOUSE_MAX_ROWS cap, which is valuable behavioral information.

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?

Two sentences with no filler. The main operation is stated first, the restriction and alternative are second, and the row cap is included without extra prose.

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?

For a one-parameter tool with one clear schema and no nested objects, the description is quite complete: it states allowed statements, describes the return behavior, clarifies limitations, and routes non-read calls elsewhere. The only minor gap is lack of detail around the exact shape or formatting rows.

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?

The input schema already documents the `sql` parameter as a single read-only SQL statement at 100% coverage. The description adds only a minor clarification of allowed statement types, which is helpful but not essential for understanding the parameter.

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 precisely what the tool executes: SELECT/SHOW/DESCRIBE queries that return rows. It also clearly separates read-only from read-write behavior by naming the non-read alternative, making selection unambiguous.

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?

The description explicitly defines when to use this tool (SELECT/SHOW/DESCRIBE) and what to do for non-read statements: use `execute` for read-write mode. This is an explicit when/when-not/alternative pattern.

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