Compare stated user intent with SQL AST target columns to detect unauthorized changes to sensitive privilege, financial, or credential data before execution.
Compare stated user prompt intent against SQL AST target columns to detect unauthorized modification of sensitive privilege, financial, or credential columns.
| Name | Required | Description | Default |
|---|---|---|---|
| sql | Yes | The SQL query to check. | |
| intent | No | The stated prompt intent or instruction. |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, but it does not say whether the tool executes SQL, is read-only, needs elevated permissions, returns findings, or what happens when it detects a violation. The single sentence only gives the detection purpose, leaving the operational profile largely unknown.
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?
It is a single front-loaded sentence with no filler; the sensitive-column categories are specific and earn their place.
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?
Because there is no output schema and no annotations, the description should say what the tool returns and how a finding is reported. It also omits usage context relative to sibling tools, so an agent cannot fully determine the invocation semantics from this definition alone.
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%, so the schema already documents sql and intent. The description maps them to 'stated user prompt intent' and 'SQL AST target columns' but does not add format, examples, or constraints beyond the schema, so 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?
It names a specific comparison operation (intent vs. SQL AST target columns) and the security outcome (unauthorized modification of sensitive columns). That is enough for an agent to distinguish it from db_query or db_dry_run, which execute or simulate queries.
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 implies usage by calling it a check for unauthorized modification, but it never says when to call it, whether it precedes db_commit or db_dry_run, or whether it can be used independently. No sibling alternatives are named, so the agent must infer routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.