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

Annotations declare destructiveHint=true, openWorldHint=true, and idempotentHint=true. The description adds valuable context: it explains the idempotency mechanism concretely (re-using the key returns original handoff), specifies that the server composes the notification body, and notes that supplying both message and reason is an error. This complements the annotations rather than merely restating them, though it doesn't detail auth requirements or what the response contains.

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?

Three sentences, each earning its place: the first defines the tool's two modes, the second clarifies field responsibilities (server composes body, callers supply contact/reason), and the third documents idempotency. No Waste words, though it could arguably be slightly tighter. Front-loaded with the core purpose.

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 12-parameter, no-output-schema tool with complex mode-dependent field semantics, the description covers the key ambiguity well: explaining mode-specific fields, the server-composed body behavior, the message/reason alias trap, and idempotency. It doesn't enumerate which fields map to which mode explicitly (e.g., purpose/agent_id for agent mode, contact_* for human), but the schema descriptions partially cover this and the description gives the critical guidance needed.

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 all 12 parameters have individual descriptions. The tool description adds general field-roles guidance (which mode uses which fields, and that message is a deprecated alias for reason). However, most of the parameter meaning is already carried by the schema descriptions, so the description provides marginal incremental value beyond flagging the message/reason relationship and mode-field mapping.

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 uses a specific verb (initiate/begin), names the resource (handoff), and clearly identifies the two modes (human operator vs. agent continuation). It distinguishes itself from siblings like request_callback (which likely just schedules a callback) by explaining the two-mode structure and the idempotent key behavior, adding scoping details.

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?

The description explicitly explains when to use human vs. agent mode ('SMS/email via lead_routing_json' vs. 'signed continuation URL'), clarifies that callers supply contact and reason fields rather than message text, and documents idempotency behavior (re-using a key returns the original handoff). This provides clear context for choosing this tool over request_callback or query_business_agent.

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