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

Annotations already declare readOnlyHint=false and idempotentHint=false, so the description's real contribution is the concrete consequence: a duplicate email is reported by iContact as a warning rather than a failure. It also names the underlying endpoint POST /contacts, which helps an agent reason about behavior. It does not say whether the warning still creates a duplicate record, which is the one ambiguity that matters most.

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: the WRITE marker leads, the list caveat follows, and the idempotency note plus endpoint close it out. Nothing is redundant and the highest-risk information is front-loaded.

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 14-parameter mutation with no output schema, the description covers purpose, list scoping, and duplicate behavior but omits the parameter surface entirely and says nothing about what comes back. Since a caller almost certainly needs the new contact's ID to subsequently call icontact_set_subscription, that return-value gap is meaningful despite the otherwise solid framing.

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 description mentions no parameters at all, while schema description coverage is only 29% — the 13 non-required fields (fax, street, status, business, name parts, etc.) are essentially undocumented anywhere, and even the required email is only implied. Given the schema does little of the work here, the description should have compensated and does not.

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 ('add one contact to the account') and immediately narrows scope by noting it does not attach the contact to a list, naming the sibling that does. An agent can distinguish it from icontact_update_contact and icontact_set_subscription without opening any 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?

Explicitly routes list-assignment to icontact_set_subscription and warns that duplicates surface as warnings rather than errors. It stops short of full routing guidance, though — it never says to use icontact_update_contact when the email already exists, which is the natural next question given the duplicate behavior it describes.

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