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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that by naming the detection categories and stating the response shape (findings with severity counts), which annotations cannot express.

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, with the use condition front-loaded and the return summary appended. 'and more' is mildly vague filler, but overall nothing is wasted.

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 single-parameter, read-only, closed-world scan with full annotation coverage and a stated return summary, the description is nearly complete. The only gap is the absence of any dialect/input-size caveat or a note on how it differs from the lint/validate siblings.

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?

Only one parameter and schema description coverage is 100%, so the schema fully documents 'sql'. The description adds no syntax, size, or dialect constraints (e.g. whether multi-statement input is allowed), leaving the baseline 3 appropriate.

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 ('SQL checked for injection patterns') and enumerates the detection classes (tautologies, UNION attacks, stacked queries, comment bypasses). It is clearly distinct from format_sql/parse_sql, though it doesn't explicitly draw the boundary against the closest siblings lint_sql, validate_sql, and analyze_sql.

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?

'Use this when the user wants SQL checked for injection patterns' gives a concrete trigger condition tied to user intent. It offers no when-not guidance and never names the adjacent siblings (validate_sql, lint_sql), so an agent must infer that security scanning is separate from correctness linting.

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