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 the stronger "IRREVERSIBLE / permanently" framing plus the requirement that user consent precede confirm=true, which is behavior annotations cannot express. The confirm mechanics partially repeat the schema's own parameter description, keeping it just short of a 5.

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?

Three short sentences, front-loaded with the "WRITE, IRREVERSIBLE" risk marker, then the safer alternative, then the consent gate. No filler and the most important warning comes first.

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 three-parameter write with no output schema, the definition covers risk level, reversibility, the safer sibling alternative, the consent prerequisite, and the underlying endpoint. Nothing an agent needs to decide whether and how to call it is missing.

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 33% (only confirm is documented), but the description compensates by spelling out the call shape — DELETE /lists/{list_id}/contacts?id={contact_id} — which clarifies that contact_id is a query parameter while list_id is a path segment. It also ties confirm=true to prior user agreement, adding intent semantics beyond the const constraint.

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?

The description gives a specific verb and resource ("permanently delete one contact from a list"), states the scope (single contact), and names the sibling it is not — vision6_update_contact. An agent can distinguish it from all other contact tools without opening a 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?

It states the intended case (privacy erasure request), gives an explicit alternative when the goal is only to stop emailing (vision6_update_contact with email_subscribed=false), and sets a precondition for invocation (pass confirm=true only after the user agreed). That is when/when-not/alternatives in three sentences.

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