Delete Portal (ADMIN)

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

The description discloses that deletion requires ADMIN authentication, and that deletion is refused if the portal has pages or accesses unless force=true. These are meaningful behavioral conditions beyond what annotations convey. The description aligns with annotations (destructiveHint=true, readOnlyHint=false), adding valuable context about safety guards and auth requirements. It could mention what happens on force-delete (e.g., whether child pages are cascaded), but the disclosed refusal mechanism is strong behavioral context.

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?

Two crisp sentences with zero waste. The first states the purpose, the second packs critical usage and safety constraints (auth requirement, refusal condition, force override). Highly front-loaded and efficient.

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?

This is a dangerous mutation tool with no annotations contradicting, destructiveHint=true properly flagged, and no output schema needed for a destroy operation. The description covers the delete semantics, the force condition, and the dryRun/force params are self-evident from their boolean defaults. With 64 sibling tools including a distinct delete_page (different target), the scope of 'portal deletion' is unambiguous. Slightly incomplete in not explaining what force=true does to child resources, but adequate for the destructive operation context.

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 shoulder the parameter explanation burden. The description references 'force=true' explicitly, explaining the one parameter with meaningful behavioral impact. portalRef is self-evident given the name, and dryRun (defaulting to false) signals a no-op simulation. It doesn't spell out dryRun's effect, but the boolean default and naming make it reasonably inferable.

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?

Specific verb+resource ('Delete a portal') clearly distinct from siblings delete_page, delete_connection, etc. The 'ADMIN' marker in the title and description clarifies the authenticated scope. The description immediately differentiates this from archive_portal, unpublish_portal, and other non-destructive portal operations.

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 description clearly states the authPrerequisite (ADMIN key) and the refusal behavior when pages/accesses exist without force=true. This effectively communicates when NOT to call this tool (when portal has children unless force is intended). It doesn't explicitly name alternatives like archive_portal for non-destructive removal, but the destructive semantics paired with the ADMIN marker make the usage boundary reasonably clear.

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