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

With no annotations provided, the description carries the behavioral burden. It discloses meaningful behavior beyond the schema: step=0 means overview, steps 1-7 are single-step guidance, and free questions are auto-mapped to relevant steps. It does not detail the response format or how conflicting step/question inputs are handled, but the disclosed automatic topic recognition is a genuine behavioral insight.

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 a single compact sentence that front-loads the purpose and immediately gives the operative input semantics. Every clause earns its place, with no filler or redundant restatement of the schema. It is easy to parse quickly.

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 two-parameter, non-destructive guidance tool, the description covers the essential invocation logic: how to use step values, when to use free questions, and what the overall purpose is. It does not explain return values, but no output schema exists and the guidance-tool nature makes that less critical. A minor gap is the lack of explicit guidance on precedence when both step and question are supplied.

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?

Although schema coverage is 100%, the description adds value beyond the raw integer and string definitions. It maps the step values to semantic modes (0 = overview, 1-7 = single step) and clarifies that the question parameter is for free-form queries with automatic topic-to-step identification. This is more meaningful than merely restating parameter names and types.

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 clearly states the tool's role: an AI customer-service step guide that walks users through a 7-step writing process. It also defines three distinct invocation modes (overview, single step, free question), which distinguishes it from the operational sibling tools like export_kd or compose_chapter. The verb-plus-resource framing is specific and actionable.

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 explains how to choose among modes via the step parameter or free-form question, which implicitly tells when to use the tool. However, it does not explicitly state when not to use it or which sibling tool should be preferred for related requests, such as frontdesk_reception or redline_audit. Usage guidance is present but mostly implied.

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