omni_audit_sqli

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

With no annotations, the description carries the full behavioral burden and does little of it. It does not say whether code is executed or only parsed, whether it is safe/read-only, whether there are depth or size limits, or what findings look like (there is no output schema either).

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?

A single front-loaded sentence that names the technique, targets, and vulnerability class with no filler. It is dense but efficient; a short follow-on sentence about output or execution model would still be warranted.

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 scanner with no annotations and no output schema, the definition covers what it scans but not what it returns or how it behaves. The critical gap is the execution model and finding format, which an agent needs in order to interpret results.

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 enum and the code/path split are already documented. The description restates the supported languages but adds no meaning about how code and path interact or which takes precedence.

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 names a specific technique (AST-based SAST), a concrete target (Python/JS/PHP/Java source code or files), and a concrete vulnerability class (SQLi / unparameterized query sinks). That is enough to tell it apart from siblings like omni_dynamic_probe or omni_obfuscate_snippet, though no sibling is named 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?

There is no statement of when to choose this over alternatives such as omni_dynamic_probe (runtime testing) or omni_triage_target, and no exclusions. The only implied guidance comes from the tool being SQLi-specific, so the agent must infer the rest.

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