truthgate_inspect_action

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

With no annotations, the description carries the full burden. It discloses the safety-oriented behavior ('block accidental destruction') but does not explain what the classifier returns, whether it blocks execution or merely reports a verdict, how false positives are handled, or what happens on a destructive match.

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 with no wasted words; the core purpose and examples are immediately clear.

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 simple one-parameter classifier this is nearly sufficient, but with no annotations and no output schema, the description should clarify the return format (classification/verdict) so the agent knows how to act on the result.

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 parameter is already documented. The description adds useful semantic examples of what the classifier detects ('rm -rf, DROP TABLE'), giving the agent concrete expectations beyond the schema's generic 'Shell command or action to validate'.

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 states a specific verb ('Classifies') and resource ('shell commands or DB queries'), plus the outcome ('block accidental destruction'). It is clearly distinct from the sibling truthgate_* tools, though it does not explicitly name or contrast them.

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?

Usage is implied: validate a command before executing it to prevent destructive actions. There is no explicit when-to-use/when-not guidance or comparison to alternatives, leaving the agent to infer the workflow.

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