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

Goes well beyond the annotations by disclosing the bounded side effect ('Opt-outs are recorded durably; nothing else is auto-routed or executed'), the pricing model ($0.03/call, waived while no payment rail is on), async execution with get_outcome, and beta status. This reconciles the apparently read-only framing ('Classify') with readOnlyHint=false. It omits auth/permission requirements and any rate limit, which keeps it short of a 5.

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 in the first clause, followed by the intent examples and bracketed operational tags. Every element is information-bearing, though the dense bracket syntax ([$0.03/per_call] [async→get_outcome] [beta]) is terse at the cost of scannability.

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 7-parameter, nested-object tool with no output schema, the description covers side effects, cost, and async retrieval of results, which is most of what an agent needs. It does not describe the shape of the suggested_action receipt, and with no output schema that return-value gap is only partially bridged.

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 is expected to compensate for the seven parameters, yet it says nothing about smb_id, raw_message, sender, inbound_channel, or received_at_iso. The listed intents (booking request, cancellation, opt-out, inquiry, complaint) describe the classification output, not input semantics, so they do not fill the gap.

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 ('Classify') and resource ('an inbound message for an SMB') plus the deliverable ('a suggested_action'), and explicitly bounds scope with 'nothing else is auto-routed or executed'. It does not name any sibling, but 'handle_inbound' is readily distinguishable from send_message, capture_lead, or escalate_to_human.

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 supplies one routing cue ('async→get_outcome') and frames the classification as advisory ('treat the intent as a hint'), which implies when to trust the result. However it never states when to use this tool versus capture_lead, escalate_to_human, or send_message, so the agent must infer the placement from the description alone.

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