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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description goes beyond them by disclosing allowlist enforcement and the failure mode ('an unknown one comes back as an error for you to relay') and by instructing a warm, brief reply after the call — behavior an agent could not infer from structured fields.

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?

Purpose is front-loaded and every sentence carries routing, fallback, or error information. It is slightly baggy: the pronoun 'It' in 'It passes the team the case' is ambiguous, and the routing guidance wraps across three sentences where two would do, but there is no filler.

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 two-parameter navigation tool with no output schema, the description covers the decisive cases: routing versus hand_over, the fallback condition, the allowlist and its error behavior, and the desired post-call reply. The only gap is what a successful call actually renders for the customer, which is minor given the annotations and schema.

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 description coverage is 100%, so both parameters are already documented, including that chatid is set automatically and that 'support' is the current allowlisted destination. The description reinforces the allowlist constraint and its error outcome but adds no new format or value detail beyond the schema, making the baseline 3 appropriate.

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 states a concrete verb+resource ('open an allowlisted place in the app for the customer') and immediately distinguishes itself from the sibling it is most likely to be confused with: hand_over. An agent can tell whether to navigate the customer or escalate to a human without reading either 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?

It gives explicit when-not guidance ('can I speak to someone', 'talk to a person', or one of hand_over's reasons) and names the alternative tool to call instead, plus the exact fallback condition for using open_destination with 'support' (hand_over returned sent=false, or the customer just wants to view the chat). Nothing 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.