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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered. The description goes meaningfully beyond that by enumerating exactly what is wiped (status, blocks, trust level, metrics, action history) and by explaining that the author is recreated with a clean record on the next moderation — a non-obvious consequence that materially affects the decision to call it.

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?

Short and front-loaded, with the key destructive consequence in the second sentence. The opening line "Delete an author" merely restates the title and name before "Delete a specific author" repeats it again, a small redundancy.

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 single-parameter destructive tool with annotations covering the safety profile and no output schema, the description supplies the consequence model an agent needs. Only the absence of alternative-routing guidance and permission requirements keeps it from being complete.

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?

The description says nothing about the id or projectId arguments. The reported coverage of 0% is pessimistic — the nested schema fields do carry useful text (external vs moderation-assigned ID, project scoping rules) — so the schema largely carries the load, but the description adds no filtering or identity semantics of its own.

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 ("Delete a specific author"), which is inherently distinguishable from the mutation siblings authors-block, authors-suspend, and authors-update. It never names those siblings explicitly to route the agent, but the verb does the differentiating work.

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 guidance on when to choose deletion over the softer authors-block or authors-suspend, nor any stated prerequisites or permissions. The agent must infer the escalation path from sibling names alone.

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