Generates up to three reasoned, asset-aware commands and typed plans from a scan intent, targets, and known assets, helping users review options before any approval or execution.
Prepare up to three reasoned, asset-aware commands and typed plans. No plan is approved or executed.
| Name | Required | Description | Default |
|---|---|---|---|
| assets | No | ||
| intent | Yes | ||
| targets | No |
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | ||
| summary | Yes |
Changes observed during successful MCP inspections.
v2.0.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds two useful behavioral facts: output is capped at three candidates and nothing is approved or executed. It says nothing about determinism, latency, or what 'asset-aware' reasoning costs, so it only mildly exceeds annotation coverage.
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 compact sentences with the capability first and the non-execution guarantee second; no filler or repetition. The terseness shades into under-specification, but the structure itself is sound and front-loaded.
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?
An output schema exists, so return values need no explanation, and annotations cover safety. But for a three-parameter tool with zero schema coverage, the description leaves the required 'intent' field, the meaning of 'typed plan', and the relationship to nuclei_plan/nuclei_execute entirely unaddressed. An agent would have to guess how to form a valid call.
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 description coverage is 0%, so the description carries the full burden, yet it explains none of the three parameters. 'Asset-aware' faintly gestures at the assets array, but intent (the only required field) and targets get no meaning, format, or example. The most load-bearing input to the tool is left completely undefined.
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 verb 'Prepare' and objects 'commands and typed plans' describe a recommendation-generation tool, and 'asset-aware' hints at the input shape. However, 'reasoned' and 'typed plans' are unexplained jargon, and the description never says these are Nuclei scan commands, so an agent must infer the domain from the tool name alone. It only indirectly distinguishes itself from nuclei_plan and nuclei_execute.
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 sentence 'No plan is approved or executed' draws a boundary but gives no when-to-use guidance, no prerequisites, and no named alternatives among the many siblings (nuclei_plan, nuclei_customize, nuclei_select_targets, nuclei_execute). An agent cannot tell from this text whether to call nuclei_recommend before nuclei_plan or instead of it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.