sql_editor_classify

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

readOnlyHint=true already covers the non-mutating nature, and the description reinforces it with 'without running anything.' However, it defines its own behavior only by reference to another tool ('Same check as sql_editor_query'), giving no detail on return shape or classification criteria beyond 'change data or schema.'

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 short sentences with no filler, and the core purpose is front-loaded before the comparison to the sibling tool. Slightly hampered by referencing another tool's behavior instead of stating its own outright.

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 simple single-parameter classification tool with no output schema, the description should describe what it returns (e.g., which statements flagged, or a classification structure). It only implies this via the opening question, leaving the result format unstated.

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 0%, so the schema supplies no meaning for the sole 'statements' array parameter. The description's 'Which of these statements' implies the input is a list of SQL statements to classify, adding some meaning, but gives no format, size, or batching details.

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 function: determining which statements require user confirmation because they change data or schema. It distinguishes itself from the sibling sql_editor_query by clarifying it performs the same check 'without running anything.' The name sql_editor_classify is opaque, but the description rescues it.

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?

It ties usage to a concrete workflow ('for "Run all"') and explicitly names the related alternative (sql_editor_query), explaining that this variant does the check without execution. It gives clear context but does not spell out explicit when-not conditions beyond that.

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