add_target

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

Without annotations, the description discloses idempotency (find-or-create), the SSRF restriction, and that it does not trigger a scan. It covers safety and side effects well, though it could mention response format or error conditions, which are not critical given no output schema.

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?

Two succinct sentences with critical information front-loaded; no extraneous words. The core purpose and behavior are stated immediately, followed by restrictions and next steps.

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 single-parameter tool with no output schema, the description fully covers purpose, behavior, restrictions, and next steps. Nothing essential is missing for an agent to call it correctly.

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 schema has no description for 'domain', but the description clarifies it is the target's domain and acts as the identifier for find-or-create. It adds meaning beyond the bare string type by implying domain uniqueness and validation context.

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 action ('add a target by domain') with find-or-create behavior, clearly distinguishing it from scan and other target tools. It conveys the resource and input precisely and differentiates from siblings like scan_trigger.

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?

Explicitly notes SSRF blocking for internal/private domains and directs follow-up to scan_trigger_by_target_id() for scanning, providing clear when-to-use and when-not-to-use guidance. This removes ambiguity about appropriate invocation.

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