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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses the payment model ($0.002 USDC per successful call via x402 on Solana) and an alternate HTTPS endpoint, both of which materially affect whether and how an agent invokes it. It also states that comments and string literals are preserved, which is behavioral context annotations cannot convey.

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 definition is front-loaded with the primary action and then grouped into formatting rules, lint rules, and invocation/payment details. It is dense and acronym-heavy, but each clause carries distinct information, so the length is justified.

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 usefully sketches the return content (statement types and referenced tables, plus lint findings). The main remaining gap is the undocumented indent/enum parameter details, but for a two-mode formatter the agent has enough to call it correctly.

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% across four parameters, so the description must carry that weight. It covers two of them loosely ("consistent keyword case" for keywordCase, "or minify" for minify) but never mentions the indent parameter, its bounds, or the enum values/defaults, leaving half the parameter semantics to inference.

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 opens with a specific verb+resource ("Format and lint SQL") and then enumerates concrete behaviors: keyword-case normalization, one clause per line, indented select lists, subqueries, comment/string preservation, and a second minify mode. It also names the specific anti-patterns the linter detects, so an agent knows exactly what the tool does without opening the schema.

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 makes the two operating modes (format vs. minify) and the lint scenario explicit, and the linter-rule list tells an agent when this tool is the right choice. There are no genuinely competing siblings (csv_to_sql only shares the SQL domain), so the absence of explicit exclusions is a minor gap rather than a serious one.

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