Start Penetration Test

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

Annotations only say readOnly=false, destructive=false, openWorld=true; the description adds real behavioral detail beyond that — the tool self-checks domain verification and returns isError rather than launching, and it consumes a credit tied to the tier. It does not describe what happens after launch beyond returning an ID, but that is low risk for a non-destructive, open-world operation.

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?

Three sentences, front-loaded with the action, then preconditions, then the return value. The aside 'so there is no need to bypass this check' is slightly redundant once the refusal behavior is stated, but no sentence 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?

Covers the action, both hard preconditions, the failure mode, and the returned handle for monitoring — everything needed to call it correctly with no output schema present. Minor gaps are the lack of any cost magnitude or concurrency limit, which the tier enum partly offsets.

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 baseline is 3, but the description adds meaning the schema does not: the tier selection determines which credit is consumed, tying a parameter to a real precondition. The repo_url white-box behavior is already in the schema, so no credit there.

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 ('Launch an AI-powered penetration test against a target URL') plus the scope implied by the tier enum. It is clearly distinguishable from siblings like turbopentest_workflow_run_pentest or turbopentest_list_pentests because it launches a new scan rather than reading or orchestrating.

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?

Gives clear preconditions: the domain must be verified and a credit must be available, and it points at turbopentest_get_credits and turbopentest_get_pentest for the surrounding steps. It stops short of contrasting against turbopentest_workflow_run_pentest, so an agent must infer which launch path applies.

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