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

Annotations already declare destructive=true and idempotent=true, but the description adds the crucial human-in-the-loop constraint that confirmed=true is required and that unconfirmed calls change nothing, plus the version-conflict recovery path. This is behavior an agent cannot derive from the annotations alone.

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?

Front-loads the destructive action, then the confirmation requirement, then the sourcing and error-handling instructions. Every clause is load-bearing with no filler.

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 mutation with no output schema, the description covers scope, prerequisites, confirmation workflow, parameter sourcing, and conflict recovery — everything an agent needs to invoke it safely and correctly.

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 100%, so the baseline is 3, but the description goes further by tying listId and expectedVersion to their source (latest library_list_get) and explaining confirmed as a user-confirmation gate. That workflow meaning exceeds the field-level schema text.

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: 'Permanently delete every completed item from an owned Library List.' It also draws an explicit scope boundary against the many sibling deletion tools by noting 'Library Lists only, not trip checklists.' An agent can distinguish it from library_list_delete, library_list_item_delete, and checklist_items_remove immediately.

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?

Gives a full when-to-use protocol: confirm the removal count with the user, call with confirmed=true only after confirmation, and source listId/expectedVersion from the latest library_list_get. It even prescribes recovery behavior on library_version_mismatch (re-read and reconsider, never retry blindly), leaving nothing to inference.

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