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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is partly covered. The description adds real context beyond them: the immediate 404 for readers, the 30-day restore window, the automatic permanent erasure afterwards, and the exact scope of what ceases to exist. However, the confirm/title-guard behavior is the only invocation-critical detail it describes, and it does not cover whether the call is rate-limited or what a successful response returns. A 3 reflects solid added context while annotations carry the safety signal.

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 dense paragraph that front-loads the destructive effect and its visibility consequences before the reversible/irreversible distinction. Every sentence carries information, though the parenthetical list of erased artifacts makes it heavier than strictly necessary.

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 two-parameter tool with no output schema, it covers effect, reversibility window, permanent consequences, blocking preconditions, and the safety input. An agent has enough information to invoke this correctly and safely.

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 coverage is only 50% (proposal_id has no description), but the description compensates: it explains that confirm must exactly repeat the page title as a wrong-deletion guard and that the target should be verified via list_proposals. The one gap is that proposal_id itself is never characterized as the page identifier.

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 plus resource ('Delete a page') with an immediate statement of the observable effect (link breaks, 404, disappears from lists, analytics and folder pages). It is clearly distinguished from restore_proposal and list_proposals, which are named in the text.

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?

Explicit preconditions and alternatives: use restore_proposal within 30 days to undo, resolve any unresolved report before deleting, and check the target with list_proposals first. This covers when to use, when it will fail, and which sibling to reach for in each case.

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