Query Clickhouse

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

No annotations are provided, so the description is the only behavioral disclosure. It does usefully state that the operation is read-only and parameterized, and that the target must be an allowed table. However, it does not explain behavior on disallowed queries, error handling, timeouts, or output amplification, and the TODO marker suggests the description is unfinished.

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?

One compact sentence, but it is front-loaded with 'TODO NIK-17', which is placeholder metadata rather than useful guidance. The remaining wording is tight and covers the core action, though at the cost of under-specification.

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 a single parameter and an output schema present, the description does not need to document return values. Yet for a tool that executes arbitrary SQL, omitting the parameterized-query syntax and how allowlisting is enforced leaves a meaningful gap; the description is minimally viable rather than complete.

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 provides zero description for the sql property, and the tool description only says it is a 'parameterized query.' It does not specify placeholder syntax, SQL dialect, statement restrictions, or an example, so the agent has to guess the expected value format beyond knowing it should be SQL.

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 names a specific action ('run') and a specific resource ('allowlisted analytics tables'), and clarifies the query is read-only and parameterized. This clearly differentiates it from ping and list_allowed_tables, though it does not name them. The TODO prefix is noise but does not obscure the meaning.

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?

No explicit guidance is given about when to choose this tool over ping or list_allowed_tables; the only hint is the phrase 'against allowlisted analytics tables,' which implies a data-query context. There are no when-to-use or when-not-to-use statements, so the agent must infer the boundary between querying and listing tables.

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