scan_trigger

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

With no annotations provided, the description must carry the behavioral burden. It does disclose a significant side effect ('finding-or-creating the Target') and lists exactly which modules run for each profile. However, it does not mention whether the scan is synchronous/asynchronous, what it returns (e.g., scan ID), or any potential error conditions. It adds value but leaves key operational behaviors uncovered.

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?

The description is a single paragraph with an front-loaded action and a well-formatted list of profiles. It is efficiently written with no redundancy, and the profile section is easy to parse. The only minor inefficiency is that profile details could be considered verbose, but they are directly useful for selection.

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?

Given the tool's complexity (find-or-create behavior, profile-dependent module execution) and lack of annotations or output schema, the description covers the core functional aspects well. It addresses the creation side effect and module scoping. It does not describe the return value or how to track progress, but these might be covered by sibling tools like get_scan_status. Overall, it is complete for a scan-trigger operation.

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?

The input schema has 0% description coverage, so the description must explain parameters. It does explain 'profile' thoroughly with all valid values and their module effects. 'target_url' is explained as 'a URL' and the behavior 'by domain' clarifies its expected semantics. While it doesn't specify exact format (e.g., must include scheme), the meaning is clear enough for an agent to use it correctly.

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 clear action ('Trigger a scan'), the resource ('a URL'), and an explicit behavioral nuance ('finding-or-creating the Target by domain'). This distinguishes it from the sibling scan_trigger_by_target_id, which presumably operates on an existing target ID, so an agent can tell them apart without extra context.

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 does not explicitly state when to use this tool versus alternatives. It implies that if you have a URL and need a scan, this is the tool, and the profile explanation gives some selection context, but there is no explicit guidance on when to prefer scan_trigger_by_target_id or any conditions to avoid this tool. The usage context is inferred rather than direct.

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