bulk_delete_targets

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so excellently. It explicitly states the irreversibility beyond a 60-second window, what is restorable (domain/tags) versus not (scan history), the required permission scope, and the mandatory confirm flag. This gives the agent a complete picture of side effects and prerequisites before invocation.

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 compact (two sentences) and front-loads the most critical facts: permanence and the irreversible consequence. It then efficiently covers the undo window, restorability, permission requirement, and confirmation flag without superfluous text. Every clause serves a purpose, making it exemplary in structure.

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 destructive two-parameter tool with no output schema and no annotations, the description covers the essential context: side effects, irreversibility, undo reference, permission scope, and confirmation requirement. It does not mention error handling or edge cases (e.g., what happens if target_ids are invalid), but given the tool's simplicity and the rich behavioral coverage, it is nearly complete. A mention of the response (e.g., success status) would fully round it out.

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?

Given the schema has 0% description coverage, the description must explain parameters. It explains 'confirm' well ('Set confirm=True to actually perform this'), but it does not explicitly describe the 'target_ids' parameter (e.g., that it's an array of target IDs or how they are specified). The schema only provides a title 'Target Ids' and type, so the description adds value for confirm but leaves target_ids inferred from the tool name, which is insufficient given the low coverage.

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 clearly states the action: 'Permanently delete targets and all their scan history/findings' with specific verb (delete) and resource (targets) plus the scope of what gets removed. It distinguishes from siblings like bulk_archive_targets and restore_target by emphasizing permanence and the inclusion of scan history, making the tool's unique purpose unambiguous.

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 provides strong usage context: it notes the 60-second undo window and points to undo_bulk_delete_targets as an alternative, and it specifies the required 'destructive' scope on the API key. It implicitly guides when to use this (permanent deletion) versus alternatives (e.g., archiving), though it doesn't explicitly say when not to use it beyond the irreversibility warning. The confirm flag is also clearly explained as the gate for execution.

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