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

With no annotations supplied, the description carries the full behavioral burden and does disclose valuable traits: credits are reserved atomically, client-supplied findings or 'completed' state are rejected, and a failed reservation or a non-starting engine costs 0 credits. It stops short of permission requirements, whether a started scan must later be closed with vulkill_complete_scan, or what the call returns.

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 core action, and the credit-charging caveat is a good closer. However the first sentence is a long, heavily parenthesized construction that is hard to parse, and the middle sentence about fake findings is phraseable more tightly.

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?

This is a complex 10-parameter mutation-style tool with no annotations and no output schema, so the description should explain more of the contract. It never clarifies the meaning of required authorizationScope, the required liabilityAccepted gate, idempotency behavior, or what a caller receives on success versus a rejected reservation.

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% across 10 parameters, so the description must compensate, and it only lights up sourceFiles and targetUrl plus a vague notion of authorization. Mode's five enum values, files, sites, started, targetName, idempotencyKey, liabilityAccepted, and the authorizationScope enum are all left to the raw schema with no added meaning.

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 verb and resource: it runs a real VulKill scan over either authorized source files (sourceFiles) or a verified live site (targetUrl), funded by an atomic credit reservation. That is far more specific than the bare name, though it never names its closest sibling (vulkill_scan_guided_interactive) to draw the boundary.

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?

Usage is only implied: the scan targets must be authorized/ownership-verified, and the account must have an API key or OAuth link. There is no explicit statement of when to pick this scan versus vulkill_scan_guided_interactive or vulkill_complete_scan, and no precondition about checking credit balance via vulkill_check_credits first.

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