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

Beyond the annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false), the description discloses concrete behavioral constraints: 500-row and 20-second limits, history only from 2025-01-01, excluded tick-level tables, and that results report which limit was hit. It also explains the no-key vs. API-key difference and links to authoritative docs.

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 somewhat long but front-loads the core action and resource, then efficiently bundles limits, key behavior, and documentation links. Each sentence contributes useful information; the two URLs are warranted because they provide the full table/limit and API references.

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 single-parameter, read-only query tool with rich annotations and no output schema, the description is complete: it explains what returns ('rows back'), applicable limits, auth behavior, and where to find deeper reference material. Nothing an agent needs to invoke it correctly is missing.

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?

There is only one parameter, sql, and the schema already describes it as 'A single SELECT statement' with 100% coverage. The description adds the ClickHouse dialect and read-only restriction, but does not need to elaborate further since the schema and description together fully specify the parameter's meaning.

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 ('Run'), a precise resource ('one read-only ClickHouse SELECT against the global_markets database'), and the immediate outcome ('get the rows back'). This clearly distinguishes run_sql from its metadata-oriented siblings like list_tables and describe_table.

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 gives clear access context: no key is needed for default limits, and connecting with an API key switches to that key's plan. It does not explicitly name sibling tools as alternatives or state when not to use run_sql, but the read-only SELECT scope and provided docs make intended usage clear.

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