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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered; the description adds genuinely new behavior in 'Comments are not kept' and the return shape {formatted_sql, options}, which no structured field supplies. It omits what happens on malformed SQL input.

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 sentences, front-loaded with the trigger, then the observable behaviors and return shape. No filler, and the useful return-value note is included despite the absence of an output schema.

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?

With no output schema, the description compensates by naming the returned object; parameters are covered by a 100%-coverage schema. The only notable gap is error/edge-case behavior (e.g., invalid SQL or comment-only input).

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 all four parameters are already fully documented in the schema; the description's restatement of the upper-case and semicolon options adds little syntax or format detail beyond that baseline.

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+resource (reformat/pretty-print SQL) and characterizes the transformation (one clause per line, optional upper-case keywords, trailing semicolon), which separates it from parse/lint/validate siblings without naming them 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 clear trigger condition ('Use this when the user wants SQL pretty-printed or reformatted'), but does not explicitly exclude alternatives such as lint_sql or analyze_sql, leaving the routing decision partly to inference.

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