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

Beyond the annotations (which only say this is a non-destructive mutation in a closed world), the description discloses the auth requirement, the downstream confirmation-code handshake, and the important side effect that team replies still route to the chat until confirmation completes. That is exactly the kind of operational context annotations cannot express.

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 access constraint and the core action are front-loaded, followed by the confirmation flow and the negative case. It is dense but every sentence carries information; only the confirmation-code sentence runs slightly long relative to the rest.

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 3-parameter mutation tool with no output schema, the definition covers authorization, the triggering intent, the post-save confirmation flow, and the exclusion case. It stops short of describing validation/failure behavior or whether a confirmation must be re-requested if the customer changes their address, which are the remaining gaps.

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 0%, so the description must carry the load, and it only partially does: it clarifies that inquiry_id comes 'from the turn' and that the address/phone is 'what they gave'. It adds no format, normalization, or mutual-requirement information (e.g., whether email and phone may both be supplied or either alone suffices) for the remaining two parameters.

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 gives a concrete verb and resource: save a customer's email or phone onto a guest conversation identified by inquiry_id. The phrase 'this guest conversation' implicitly separates it from business-level siblings like confirm_business_email or contact_business, though it never names an alternative tool explicitly.

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 states the triggering condition ('When the customer wants follow-up by email or text') and an explicit exclusion ('If they prefer chat only, do not call this'). It also states a prerequisite up front ('Owners only (needs sign-in)'), so an agent knows both when to invoke and when not to.

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