runQuery

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: the endpoint refuses write operations, row limits are backend-applied, and the offset parameter has a specific server-side implementation (fetches offset+rowNumber rows and returns the tail). This is useful behavioral disclosure that goes beyond what annotations provide.

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?

Three sentences with zero waste. The core purpose is front-loaded, the constraint (read-only SELECT) is stated early, and the alternative tool is named in the same sentence as the exclusion. Every sentence earns its place.

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 read-only query tool with 100% schema coverage and no output schema, the description covers the essential context: what it does, what it refuses, when to use the alternative, and the row-limit behavior. The only minor gap is that it doesn't describe the return format or error behavior, but with annotations covering the safety profile and schema covering parameters, this is nearly 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?

Schema description coverage is 100%, so the schema already documents all four parameters. The description adds some context about row limits ('ask for what you need with UP TO n ROWS') and the offset behavior ('add an ORDER BY to make the window stable'), which supplements the schema. However, the description doesn't add meaning for the decode parameter or sqlQuery beyond what the schema provides. Baseline 3 is appropriate when schema does the heavy lifting.

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 specific resource ('Open SQL SELECT'), and the expected outcome ('get the rows back'). It explicitly lists supported SQL features (joins, aggregates, GROUP BY) and clearly distinguishes itself from runSnippet, which is a sibling tool. This is a clear, specific, and well-differentiated purpose statement.

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 states when to use this tool ('Reading only, and only SELECT') and when NOT to use it ('the endpoint refuses anything that writes'). It also names the alternative tool (runSnippet) and the conditions that select it ('for logic around the data (call a function module, compute, loop)'). This is explicit when/when-not guidance with a named alternative.

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