business_classify_reply

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

With no annotations provided, the description carries the full behavioral burden and does so strongly: it explicitly states the tool is read-only, mandates human-review routing for sensitive/low-confidence cases, and prohibits copying raw reply text into workflow-improvement telemetry. These are non-obvious behavioral constraints an agent needs before invoking the tool.

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 compact and front-loaded: the core purpose appears in the first sentence, followed by three crisp, high-value behavioral constraints. Every sentence earns its place, with no filler or repetition of schema information.

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?

Given the tool has an output schema and only one required parameter, the description covers the critical behavioral context: read-only nature, human-review routing triggers, and telemetry privacy. It is slightly incomplete in not distinguishing this tool from sibling classification tools and not clarifying the format of taxonomy or thread_context, but overall it is highly usable.

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 0%, so the description must compensate. It does add meaning for weather conditions like 'inbound reply' maps to reply_text and 'low-confidence' maps to confidence_threshold, and the telemetry warning clarifies handling of reply_text. However, it leaves channel, taxonomy, project_ref, and thread_context semantically unaddressed beyond their names and defaults.

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 states a specific action ('Classify an inbound reply') and a distinct outcome ('propose a governed next workflow event'), making the tool's purpose clear. However, it does not explicitly differentiate itself from the sibling crm_classify_reply, relying instead on the 'business' name prefix and the 'governed' framing.

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 clearly signals when this tool is appropriate: for classifying inbound replies and proposing governed workflow events. It also adds valuable conditional guidance by enumerating cases that must route to human review (low-confidence, legally sensitive, disputed-payment, security, ambiguous opt-out). It stops short of explicitly saying when not to use this tool versus alternatives like crm_classify_reply.

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