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

Beyond the annotations' read/write hints, the description discloses async-by-default execution with a pointer to get_outcome, and records cost and latency. It also describes side effects such as enrichment and routing/escalation. It omits details about immediate response shape and failure behavior, but the core behavioral traits are disclosed.

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 organized into a terse purpose sentence, a matching example, explicit usage sections, and operational metadata. Every block earns its place, and the most important behavioral facts (async execution, cost, latency) are easy to scan.

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 an async tool with no output schema, the description covers selection criteria, invocation example, execution mode, and cost/latency. It tells the agent to retrieve the result via get_outcome. It does not specify what the immediate receipt or final outcome contains, which would be the remaining gap for a fully self-contained definition.

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 only 29%, so the description needed to compensate. The worked example maps the three required parameters (smb_id, inbound_channel, raw_message) to concrete values, which is useful. However, optional parameters such as sender, routing_rules, idempotency_key, and received_at_iso receive no semantic guidance in the description beyond what the sparse schema provides.

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 opening sentence states a specific verb-resource pair: receive, classify, and route inbound messages for an SMB, and enumerates concrete intent classes (booking request, cancellation, inquiry, complaint). This clearly distinguishes it from outbound tools like send_message and from escalation-only tools.

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 WHEN TO USE section gives concrete scenarios (contact-form submissions, SMS replies, voicemails, email inquiries), and WHEN NOT TO USE explicitly excludes outbound communications and compliance-flagged lists without opt-in verification. It does not name sibling tools to select instead, so it stops just short of full alternative routing.

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