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

Annotations already declare destructiveHint=true, telling the agent this is a mutating operation, so the description only needs supporting context. It adds the shared-address-book scope and the REST endpoint mapping, but says nothing about auth/permission needs, duplicate handling, or whether a failure leaves partial state. Note destructiveHint=true on a create tool is aggressive flagging, but the description does not contradict it.

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 with zero padding; the purpose leads and the constraint follows. The closing "Aircall REST: POST /contacts" is marginally useful mapping info but does not help an agent select or invoke the tool, so it slightly dilutes an otherwise tight definition.

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 create tool with no output schema, the description should say what comes back (e.g. the new contact's id) so the agent can chain into get_contact or update_contact. It also omits required permissions. Given the annotations cover safety and the schema fully documents fields, this is adequate but has a visible 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 a cross-parameter constraint the schema cannot express: the schema lists no required array at all, yet the description states at least one of first_name/last_name/company_name is needed. That is real added meaning beyond the structured fields.

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?

"Create a new contact in the shared address book" gives a specific verb+resource that is immediately distinguishable from the get/update/list contact siblings. It stops short of the 5 tier because it never names an alternative or boundary case; the distinction is carried mostly by the verb in the name.

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?

The description supplies a validity precondition ("typically requires at least one of first_name / last_name / company_name"), which is useful when composing a call. However it gives no when-to-use vs when-not guidance, no exclusions, and does not mention the related update_contact or search_contacts siblings, so usage is only implied.

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