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

Annotations already declare destructiveHint=true and non-idempotency, but the description adds material context the annotations cannot: the irreversibility of the operation (with the sole unmerge-after-merge exception) and the human-approval gate that applies by default. Both 'what gets destroyed' and 'auth needs' are disclosed, which is exactly the value a destructive tool description should add.

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?

A single sentence that front-loads the usage trigger and then qualifies irreversibility and approval. No filler or redundancy; every clause carries information an agent needs before invoking.

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?

With an output schema present, return values need no explanation, and annotations plus the description cover the safety and approval story. The only soft spot is that 'all their data' does not specify the cascade scope for related objects (calls, journal, timeline), leaving an agent to infer the blast radius.

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 contact_id and approval_id are fully documented in the schema, which sets the baseline at 3. The phrase 'requires approval by default' loosely relates to approval_id's optional nature but does not explain its single-use semantics or how to obtain it, so it adds only marginal meaning beyond the schema.

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 (remove a contact) and adds destructive scope ('and all their data'), so an agent knows exactly what is being deleted. It does not, however, distinguish itself from adjacent siblings like contacts.merge, contacts.unmerge, or contacts.update beyond naming unmerge as a recovery path rather than an alternative.

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 a clear selection trigger: use only when the user explicitly asks to remove a contact, and notes approval is required by default. No explicit 'when-not' or named alternative is provided, so the routing guidance is solid but not exhaustive.

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