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

Annotations declare readOnlyHint=false and destructiveHint=false, establishing that something is written but nothing dangerous is destroyed. The word 'preview' adds real behavioral context beyond the annotations, but it also creates tension with readOnlyHint=false: an agent cannot tell whether a pending action is created, whether a confirmation token is returned, or how long the preview survives. It does not state that no visibility change occurs until confirmed.

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. It is appropriately terse, though the terseness borders on under-specification for a tool with a downstream confirm step.

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 non-read-only tool with three undocumented required parameters, no output schema, and a preview/confirm workflow implied by siblings, one sentence is not enough. An agent lacks the follow-up step, the effect of each enum value, and any idempotency/expiry expectations.

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 three required parameters, and the description mentions none of them. The two enums (PUBLIC/PRIVATE, and the four resource types) are partly self-describing, but resourceId, the required visibility semantics, and the valid resourceType set receive no explanation anywhere in the description.

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 gives a verb (preview) and an object (publishing/unpublishing a resource's visibility), so the general intent is discernible. But it conflicts in emphasis with the tool name ('change'), leaving it unclear whether this actually applies a change or only computes one, and it draws no distinction from siblings like geobble_confirm_action that presumably follow it.

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?

There is no statement of when to call this versus geobble_confirm_action, geobble_resource_share_grant, or geobble_resource_delete/restore. Given the strong preview/confirm sibling pattern (geobble_confirm_action, geobble_cancel_action), the absence of any routing guidance is a clear gap.

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