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

The destructiveHint=true annotation already signals a mutating operation, so 'WRITE.' is mostly redundant, but 'nothing is sent' meaningfully disambiguates a non-obvious naming risk and the description discloses the return shape ('Returns the new contact with its id'). It stops short of permissions, duplicate handling, or idempotency behavior.

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?

Four tight fragments, front-loaded with the operation type, then purpose, then the input constraint, then the return and endpoint. Every sentence carries unique information with no repetition of schema or annotation content.

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 15-parameter, all-optional mutation with no output schema, the description supplies the critical missing piece (the effective required-field rule) and the return value. It leaves secondary behavior such as duplicate detection or field-conflict resolution unaddressed, which is a minor gap at this complexity.

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 real semantics the schema lacks: it identifies 'name' as the address-book label and states a cross-field requirement (at least one of name/company/lastname) that is invisible in a schema where 0 parameters are required.

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 ('Adds a contact to the address book') and preempts the most likely confusion by noting it is not a customer message and sends nothing. That distinction lets an agent separate it from vyfakturuj_create_invoice and the messaging-style siblings without opening a 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?

Provides a concrete precondition for use ('Give at least a name ... or company or last name') and clarifies the negative case (nothing is sent). It does not, however, point to any alternative sibling tool or describe when to prefer lookups or list tools instead.

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