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

With no annotations provided, the description carries the full burden, and it delivers. It discloses that VITNA evaluates but does not enforce, that unclaimed trial keys get only a decision label while claimed keys get full detail, that a signed audit record is produced, and that the tool is not a sandbox. This is rich, honest behavioral context beyond what any schema could convey.

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 long but every sentence earns its place: purpose, timing, response shapes, audit behavior, enforcement boundary, and limitation are all compressed into a tight, front-loaded paragraph. The critical call instruction appears near the beginning, and the caveats are placed at the end where they belong.

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?

There is no output schema, so the description must explain the response shape, and it does in detail: decision values, key-dependent detail, threat categories, severity, reason, threats array, redacted echo, and signed audit. Given the 3-parameter schema and the important key/claim nuance, nothing material is missing for an agent to call this 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?

Schema description coverage is 100%, so the schema already documents action, payload, and action_type. The description adds broader context about scanning proposed actions and redaction behavior, but it does not materially extend the meaning of individual parameters beyond what the schema provides. Baseline 3 is appropriate.

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 opens with a specific, capitalized purpose: a safety/oversight check before dangerous or destructive actions. It names concrete action categories (shell, file deletion, DB, network) and clearly distinguishes this from mere validation tools by stating it flags dangerous patterns and returns a decision. It is strongly differentiated from siblings like vitna_claim and vitna_help.

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?

It explicitly tells the agent to call this BEFORE running the action, lists when it applies (shell, file deletion, DB, network), and instructs how to treat blocked/flagged results: stop and get human approval. It also provides a when-not: it is a heuristic match, not a sandbox, so novel or obfuscated payloads can pass.

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