smokeball_create_contact

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

Annotations already flag not-read-only, open-world, idempotent, and destructive; the description adds useful context by saying routes are limited to the governed connector authority and that effect is claimed read/write and verified by Spring. It also explains approval_ref's role in resuming writes and idempotency_key as a stable business-action identity. This exceeds annotation coverage without contradicting 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?

The args list is compact and scannable, and the routing/approval notes are relevant. But the first sentence is largely a restatement of the tool name and does not add a functional definition. The description is efficient but not optimally front-loaded with purpose.

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 governed connector tool that is open-world, destructive, and has 0 required params in schema, the agent needs to know how to authorize, which identifiers to supply, and what to put in arguments; the description omits all of these. It provides routing and approval mechanics, and an output schema exists so return format needn't be repeated, but the invocation semantics for actually creating a Smokeball contact are incomplete.

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 compenses for 0% schema coverage by labeling all seven params, including project_id, project_ref, connector_account_ref, idempotency_key, effect, and approval_ref. However, the critical `arguments` parameter is only described as a JSON string for the connector operation; no contact fields or structure are specified. All params are optional in the schema and the description does not say which are needed to actually create a contact.

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 description never states that this tool creates a Smokeball contact; the opening sentence only restates the tool name as a connector operation. The routing constraint and parameter list do not define the functional purpose, so an agent must infer behavior from the identifier.

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?

There is no guidance on when to choose create_contact over related tools such as smokeball_api_request, smokeball_add_layout_contact, or the other create_* siblings. No prerequisites, exclusions, or connector account setup steps are given. The routing line is a constraint, not usage direction.

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