decision_card_to_policy_bundle

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

With no annotations present, the description carries the full behavioral burden and does well: it declares read-only semantics, the exact output flags (preview_only=true, enforceable=false), the error behavior for approved cards, and the security warning about not using output as a grant. It does not explain how inputs are resolved or what other failure modes exist.

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 core purpose and the preview_only/enforceable flags are front-loaded, and every clause carries information. The middle clause is long and dense, but nothing is redundant padding.

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 two-parameter tool with no annotations and no output schema, the description covers the safety and status semantics well but is silent on the inputs and on the shape of the returned bundle beyond two booleans. An agent could still invoke it, but with avoidable ambiguity about what to pass.

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% and neither of the two parameters (url, document_json) is mentioned anywhere in the description. The agent must infer that url points at a Decision Card document and document_json is its inline content; that inference is plausible from context but never stated, so the description fails to compensate for the coverage gap.

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states a specific action and scope: producing a read-only deny preview bundle for Decision Cards in rejected, withdrawn, expired, or pending states. This meaningfully distinguishes it from siblings like decision_card_inspect or decision_card_validate, though the name itself is opaque enough that it relies heavily on the description.

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 gives an explicit when (non-approved card statuses), an explicit when-not (approved statuses error out), and names the alternative authority (the live policy engine) that must be used instead for enforceable bundles. The closing prohibition on treating output as an access grant leaves nothing to inference.

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