extract_metadata

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds the return contract {tables, columns, functions}, which is the only place the agent learns output shape since there is no output schema. It does not say what happens with unparseable or dialect-specific SQL.

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, zero filler: the trigger condition comes first and the return shape second. Nothing is repeated from the schema or annotations.

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 one-parameter, read-only, idempotent extraction tool this is nearly sufficient: usage trigger, output keys, and a fully documented parameter. The only missing element is failure behavior for invalid SQL, which is minor given the low complexity and full annotation coverage.

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 the single "sql" parameter is already fully documented as "The SQL string to analyze." The description adds no syntax, dialect, or size guidance beyond that, so the baseline 3 applies.

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 and resource: it extracts the tables, columns, and functions a SQL query references. The output-key enumeration makes it distinguishable from siblings like format_sql or lint_sql, though it never explicitly contrasts itself with parse_sql or analyze_sql, which could sound similar to an agent.

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 ... (e.g. for lineage or impact analysis)" gives a clear triggering condition plus concrete scenarios. It does not, however, name an alternative tool or state when NOT to use this one versus parse_sql/analyze_sql.

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