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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds real value beyond that by disclosing the retention behavior of the address (it stays unsubscribed or blocked if it was), which an agent could not infer from annotations or schema. It stops short of stating irreversibility or any permission requirement, so it is strong but not 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?

Three short sentences, each doing distinct work: what is deleted, what survives the deletion, and where to go instead. The most decision-relevant content (the erase_email alternative) is placed last but the first sentence front-loads the action itself, so nothing is buried.

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 one-parameter destructive tool with full annotation coverage and no output schema, the description covers the essentials: scope of deletion, side effects on subscription state, and the privacy-request escape hatch. The only real gap is the unexplained contact_id, which the schema leaves at 0% coverage.

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?

There is one parameter, contact_id, and schema description coverage is 0%, so the description carries the full burden of explaining it. The description never mentions the parameter at all — no format, no source, no note on whether it is an ID or email address. With a single undocumented parameter the omission is significant, though the surface area is small enough to keep this above a 1.

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 names a specific verb and resource ('Delete a contact') and immediately narrows scope by stating what else is removed ('with its tags and attributes'). It also distinguishes itself from the closely related sibling erase_email, so an agent can separate the two without opening either 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 gives an explicit routing rule: for a privacy request that must remove every trace of a person, use erase_email instead. That is a concrete when-to-use-this-versus-alternative statement rather than an implied one.

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