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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, but the description adds real value beyond them: duplicate contacts may be created on repeat calls, and group_name silently CREATES a group as a side effect. That side-effect disclosure is the kind of context annotations cannot express. It stops short of 5 because it does not state auth/permission needs.

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?

Six tightly packed sentences, front-loaded with the write scope and the invocation constraint, with no filler. Every clause carries either a requirement, a side effect, or a routing hint.

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?

Important for a tool with zero required parameters — the description supplies the 'at least a name or a number' constraint the schema cannot. Since no output schema exists, it could have said what is returned (e.g., the new contact id), which is the only 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?

Schema coverage is 100% so the baseline is 3, but the description adds cross-field meaning the flat schema cannot: the at-least-one-of-name/number constraint, the group_ids (existing only) vs group_name (auto-creating) distinction, and a concrete international number example. These are genuine semantic additions, not restatements.

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?

Opens with an explicit verb+scope ('WRITE: adds one contact to the Notifyre address book'), which immediately separates it from the read-oriented siblings like notifyre_list_contacts and notifyre_get_contact. The endpoint note (POST /addressbook/contacts) reinforces the write nature.

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?

Gives concrete invocation guidance: 'Give at least a name or a number', plus the group_ids-vs-group_name choice rule and the duplicate-creation caveat. It does not explicitly route the agent against the sibling notifyre_add_contacts_to_groups for post-creation grouping, so it falls short of a full 5.

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