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

The description says "Preview moving ... to trash," which implies a non-mutating dry run, while annotations declare readOnlyHint=false, destructiveHint=true, and idempotentHint=false. The agent cannot tell whether calling this trashes the resource or merely reports what would happen, or whether a follow-up confirm_action is required. This is a direct conflict with the structured safety metadata.

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 efficient, though the brevity is partly under-specification rather than disciplined economy.

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 destructive operation with no output schema and zero parameter documentation, the description supplies almost nothing: no confirmation flow, no restorability (resource_restore exists as a sibling), no permissions, no effect on children or shares. An agent would be guessing at the consequences of a destructive call.

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 carries the burden for both parameters. It does implicitly enumerate the four resourceType values, which adds some value over the enum, but says nothing about resourceId (validity, not-found behavior, cross-type scope) or what resourceType governs beyond the type list. Not enough 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 names a verb ("preview moving ... to trash") and enumerates the four affected resource types (source, collection, map, project), matching the resourceType enum. But it conflicts with the tool name (resource_delete) and title ("Move a resource to trash") about whether the call actually mutates anything, so an agent cannot be confident what the tool does. It also doesn't distinguish itself from resource_restore or confirm_action.

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 alternatives. The sibling list contains confirm_action, cancel_action, and resource_restore, which strongly suggest a preview-then-confirm workflow, but the description never mentions that flow or any prerequisites. Usage must be inferred entirely from the name.

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