crm_classify_reply

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

The annotations already signal mutation and destructiveness (`readOnlyHint=false`, `destructiveHint=true`), and the description adds useful context that execution is scoped under the caller's JWT, tenant, and company. It does not describe what side effects `classify_reply` may have, but the annotations carry much of that burden. No contradiction with annotations.

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 short and front-loaded: the first sentence identifies the action, the second gives routing/scope context, and the Args section documents parameters. Every sentence earns its place, though it could be slightly more informative per sentence.

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?

Even with an output schema and annotations present, the description is incomplete for an agent that must decide whether to call this tool. It omits what `classify_reply` does, when it is appropriate, and what inputs the underlying action expects. The sibling list contains several overlapping CRM and dispatch tools, so this lack of semantic context is a real selection risk.

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 define `message` as a free-text objective and `inputs` as an optional JSON string, which adds meaning beyond the bare schema names and defaults. However, it gives no examples, expected keys, or structure for the `inputs` JSON, leaving ambiguity about how to invoke the action correctly.

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 concrete action—run the crm domain agent action `classify_reply`—and clarifies that it goes through the domain-agent dispatcher, so the mechanism is clear. However, it never explains what `classify_reply` actually does or what outcome the agent should expect, leaving the purpose vague beyond the name. It also does not distinguish itself from the similar `business_classify_reply` sibling.

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?

There is no guidance on when to use this tool versus alternatives such as `crm_chat`, `business_classify_reply`, or `dispatch_domain_agent`. The description only states that it routes through the dispatcher and defines parameters; it never gives selection criteria, exclusions, or prerequisites.

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