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

The description goes well beyond the annotations (which only indicate non-read-only, non-destructive, non-idempotent) by disclosing critical behaviors: best-effort source ingest and bot activation (app is still created if later steps fail), asynchronous crawl/embedding that continues after return, a per-step log including appId, internal auth mode switching, error handling with partial step log on app creation failure, and best-effort restoration of the previous auth mode. These details are essential for an agent to correctly interpret outcomes and handle failures, and they are not contradicted by the 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 structured logically: first the core purpose, then the best-effort and async caveats, then auth and error behavior, and finally the related variant. Every sentence delivers necessary information without redundancy or filler. The front-loaded purpose sentence immediately tells an agent what the tool does, and the subsequent details are packed but concise. It is appropriately sized for the complexity of the tool.

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's complexity (14 parameters, multi-step orchestration, auth switching, async behavior), the description covers all essential aspects: the overall flow, failure semantics, async continuation, auth requirements, return value (per-step log with appId), and related tool. There is no output schema, but the description mentions the key return element. Nothing an agent needs to call this tool correctly is missing, and the description is sufficiently detailed for a high-complexity operation.

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?

The input schema provides descriptions for all 14 parameters (100% coverage), so the description does not need to repeat their definitions. The description does add some contextual meaning, such as noting that source ingest is best-effort and that crawl/embedding continues asynchronously, which affects how the `docs`, `crawlUrl`, and `followLink` parameters should be interpreted. However, this is supplementary; the schema already covers the parameter semantics adequately, so a baseline of 3 is appropriate.

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 opens with a precise, actionable statement: 'One-call B2B orchestrator: create an app, set it as the current context, index RAG sources, then configure and enable its AI bot.' It names the exact sequence of operations and the resources involved, and it distinguishes itself from a sibling by naming `ethora-b2b-app-provision` as the rooms+tokens variant. This leaves no ambiguity about what the tool does or how it differs from similar 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 description explicitly mentions the related variant `ethora-b2b-app-provision` and frames this tool as the one-call orchestrator, implying it is the right choice when you want to perform all steps in a single invocation. It also states the auth prerequisite (B2B mode) and notes that source ingest and bot activation are best-effort, which influences whether this is appropriate for a given use case. However, it does not enumerate all possible alternatives (e.g., individual tools like ethora-app-create + ethora-sources-docs-upload), though that omission is acceptable given the tool's self-description as an orchestrator.

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