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

Annotations cover the safety profile (destructive, not read-only, not idempotent), and the description adds material behavior beyond them: a ticket is written to the operator queue, no notification is sent, no response time is promised, the call costs $0.2, and it runs async. This is exactly the extra context an agent needs before a mutating escalation.

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?

Front-loaded with the action and its payload, then side effects, then bracketed cost/async/beta tags. Dense and largely waste-free, though the three bracketed tags are terse metadata that an agent must decode.

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 destructive, non-idempotent mutation with no output schema, the description covers side effects, cost, async follow-up via get_outcome, and beta status. It leaves the enum-valued reason and priority parameters unexplained, which is the main gap.

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 only 20% across 5 params, so the description carries some burden. It enumerates the context bundle contents (transcript, prior actions, identifiers, recommended next step), partially compensating, but adds nothing about the reason enum values, priority semantics, or smb_id. Baseline 3 given partial compensation.

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 ('hand off') and resource ('an in-flight task to a human operator') plus what the handoff carries (context bundle). This is clearly distinguishable from siblings like send_message or get_outcome.

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?

'Hand off an in-flight task' plus the reason enum values imply when to reach for this over messaging siblings, and '[async→get_outcome]' points at the follow-up tool. It never states explicit exclusions or when NOT to escalate, so it stops short of a 5.

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