preview_write

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

With no annotations, the description carries full burden. It clearly states non-destructive behavior (preview only), lists acceptable statement types, and outlines the required user confirmation step. Could add token expiry or error handling details.

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 concise and front-loaded with key information: purpose, operations, output, non-execution guarantee, and LLM instructions. No redundant sentences.

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?

Given the simple tool (1 param, no output schema), the description covers essential aspects: what it does, its output, and its place in the workflow with confirm_write. Lacks details on token expiry or response format but is sufficient for basic usage.

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 coverage is 100% with a brief description. The tool description adds value by listing the specific statement types accepted and explaining the preview purpose, going beyond the schema's generic wording.

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 clearly states it previews write operations (INSERT, UPDATE, DELETE, CREATE, ALTER, DROP, TRUNCATE) and returns preview info and a token. It explicitly says it does not execute writes, distinguishing it from confirm_write and other siblings.

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 explains this is step 1 of a two-phase confirmation, requiring user confirmation before proceeding to confirm_write. It implicitly distinguishes from read-only tools and provides clear context, though no explicit 'do not use if' guidance.

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