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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real consequence detail the annotations cannot: addresses stop working, including printed QR codes and already-shared links. It stops short of covering partial-failure behavior with a batch of ids or any permission/scope requirements, so it is strong rather than exhaustive.

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 sentences, front-loaded with the action and id source, then the consequence and the safer alternative. Nothing is redundant with the title or schema.

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, non-read-only tool with no output schema, the description covers what breaks, why to confirm, and the reversible path — enough for correct invocation. Batch semantics (partial failure, max 200) and return value are the remaining omissions.

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 schema describes site_id and user_goal but leaves link_ids bare (items only, 67% coverage); the description compensates by saying ids come from list_links. It does not mention that up to 200 ids can be passed in one call, which is the one notable 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?

States a specific verb and resource ("Remove tracked links") and immediately scopes the identifier source to list_links. An agent can distinguish it from siblings like update_link, delete_page, or remove_redirects without opening the schema.

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 an explicit precondition ("confirm with the user first") and names the concrete alternative for the non-destructive case ("pausing with update_link is the reversible option"). This is exactly the when/when-not/alternative structure that distinguishes a 5.

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