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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context: it operates under the logged-in user's effective rules (an auth/identity dependency) and uses 'the same rule-matching semantics as the edge' (a fidelity guarantee), which tells the agent results are authoritative previews rather than approximations.

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?

A single front-loaded sentence with no filler; the simulated object, the rule source, and the fidelity claim all appear before any optional detail. Slightly dense but every clause carries information.

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?

With no output schema, the description should describe what the preview returns (a verdict? matched rule? block reason?), which it only gestures at with 'what Shield would do'. Combined with an unexplained 'path' parameter, the definition is adequate but leaves real gaps for a simulation tool whose output shape is its whole point.

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 must carry parameter meaning. It clarifies that package and version form a single package@version request and that referer/origin are optional contextual inputs, but the fifth parameter 'path' is never mentioned and no format examples are given for origin or referer.

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?

States a specific verb and resource ('Preview what Shield would do for one package@version request') and scopes it to the logged-in user's effective pin/block rules. It does not explicitly contrast itself with the sibling shield_check_packages, so an agent must infer that this is the single-request simulation versus the batch check, but the core purpose is 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 word 'Preview' and 'Simulate' imply a safe dry-run use case, and the parenthetical '(optionally with referer/origin)' signals when the extra contextual parameters matter. However, there is no explicit when-to-use/when-not guidance and no named alternative sibling, leaving the agent to reason about choosing this over shield_check_packages.

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