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

Annotations already signal destructiveHint and non-read-only behavior. The description adds useful behavioral context: async execution by default, the need to use get_outcome for the result, cost, and latency. It could further explain the irreversible or externally visible side effects of escalation, but the hand-off framing plus annotations cover the essential safety profile.

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 description is longer than average, but every section—example, when to use, when not to use, cost, latency, execution mode—earns its place and is front-loaded with the core purpose. There is no redundant 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 complex async tool with no output schema, the description supplies the critical operational details: async execution, result retrieval via get_outcome, cost, latency, when to escalate, and when not to. An agent has enough information to invoke it correctly.

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 low, but the description compensates by naming the context fields, showing a full example call, and indicating how reason, context, priority, and smb_id are used. It does not define every enum value or nested subfield, but the schema enumerations and example fill most gaps; idempotency_key is well documented in the schema itself.

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 and resource: hand off an in-flight task to a human operator with a context bundle. Includes the exact bundle contents and a concrete example query, which makes the tool's purpose unmistakable and distinguishes it from sibling tools like get_outcome or send_message.

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?

Explicitly provides WHEN TO USE and WHEN NOT TO USE guidance, including the key exclusion 'Do not use as a first resort.' This directly helps the agent decide between this tool and automated alternatives.

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