workload_test_statement

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

Annotations already declare readOnlyHint=true, and the description adds real behavioral context: non-read-only statements are not executed, only placeholder-checked, and the result reports time/rows/error. This is useful beyond the annotation, though permissions or rate/side-effect details are absent.

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 tight sentences that front-load the action and outputs before the read-only constraint. No filler, though the parenthetical '(placeholders filled in)' is slightly cryptic.

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?

The description does state the return content (time, rows, or error), which is helpful since there is no output schema. But the unexplained 'database' parameter and vagueness on placeholder substitution leave gaps for a 2-param tool.

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?

With schema coverage at 0%, the description must carry parameter meaning. It hints that the SQL may contain placeholders to be filled in, but never explains the 'database' parameter or the placeholder mechanism, leaving half the parameters undocumented.

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?

States a specific verb and scope: 'Run one statement once' to check it, listing what it yields (time, rows, or the error). This clearly separates it from bulk siblings like workload_run, though it does not name any alternative explicitly.

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?

Gives a genuine usage constraint: 'Read-only statements only; others are only checked for placeholders.' This tells the agent when the tool actually executes SQL and when it merely validates it. It stops short of naming a sibling to use instead for full execution.

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