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

Annotations declare readOnlyHint=false and destructiveHint=false; the description adds real value beyond that with the no-outbound-message guarantee and the two-phase preview/confirm write pattern. The credibility of the confirm guidance is undercut because 'confirm' does not appear in the input schema, which forbids additional properties.

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 sentences, front-loaded with the core action and immediately followed by the safety boundary and operation list. "Returns the response envelope; follow the primary nextAction" is boilerplate-ish but brief.

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?

With 18 parameters and an output schema present, the description needn't explain returns, and it doesn't. But for a tool this broad it gives no per-operation field guidance, and the phantom confirm parameter leaves the agent unsure whether a preview flow is actually supported.

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 18 parameters are already documented, and the description's operation list merely restates the operation enum. The one novel parameter claim — a 'confirm' flag — refers to a property absent from a schema with additionalProperties: false, adding confusion rather than meaning.

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 first sentence states a specific verb set (save/update) and resources (contacts, interactions, documents), and the operation list makes the six write modes explicit. It doesn't, however, say how it differs from siblings like create_item or update_item, which overlap on generic write semantics.

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?

It draws a clear negative boundary ("Never sends a message or submits an application to an employer") and prescribes the preview-then-commit flow with confirm: false / confirm: true. It stops short of naming alternative tools for adjacent jobs, so routing between log_job and create_item/update_item is left to inference.

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