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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds two things they don't: the 30-day recoverability ceiling with permanent erasure afterward, and that the restore is recorded on the contact's timeline under the acting user. That audit-visibility detail is genuinely useful and not derivable from structured fields.

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 short sentences, front-loaded with the action and the time constraint. There is minor redundancy with the title ("Bring a deleted contact back" repeats verbatim) and the circumlocution "The bringing back" where "the restore" would be tighter, but there is no padding.

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 mutation with no output schema and full annotation coverage, the description carries the needed constraints: eligibility window, irreversibility past it, and audit behavior. It omits what happens to related records (deals, activity) that referenced the deleted contact, a modest remaining gap.

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 a single parameter, id, and schema coverage is 100% ("Row id (uuid)"), so the schema fully documents the input. The description adds nothing about how to obtain the id or whether it accepts only deleted-contact ids, so the baseline 3 applies.

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 first sentence names a specific verb and resource — reviving a deleted contact — which cleanly separates it from delete_contact and create_contact. It does not explicitly name siblings, but the 'deleted contact' qualifier makes the inverse relationship to delete_contact unambiguous.

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 eligibility window (within 30 days) and an explicit failure condition (after that the contact is erased for good), which is real when/when-not guidance. It stops short of naming a sibling alternative such as restore_a_deal for non-contact undo cases, so it falls one step below the top.

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