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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description adds real behavioral context beyond those: omitting roomJid triggers a fan-out side effect across every room, and the tool depends on the ai-service being live. This scope-expansion warning is exactly the kind of trait an agent needs and the annotations do not convey. No contradiction with 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?

Three dense clauses with zero waste: purpose+endpoint, the roomJid fan-out caveat, and the ai-service prerequisite. The verb and resource are front-loaded, and every sentence earns its place for a 4-parameter 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?

For a simple flat 4-param tool with no output schema and no nested objects, the description covers the essentials: what it does, the key broadcast nuance, and a runtime prerequisite. The one notable gap is that it never states whether test messages are visible to real room participants or confined to diagnostics — important given the fan-out behavior can send messages into many rooms at once. Minor, but worth having.

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 50% — text and roomJid carry descriptions, while botInstanceId and agentIdOrAddress are bare. The description partially compensates: the endpoint pattern (:idOrAddress, :botInstanceId) clarifies the roles of the two undocumented required params, and the fan-out statement reinforces roomJid's broadcast semantics. But it adds nothing about text and doesn't fully define the two bare params, so it meets the compensation bar only partially.

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 verb and resource — "Send a test message from a BotInstance" — and pins it with the exact endpoint (POST /v2/agents/:idOrAddress/bot-instances/:botInstanceId/test-message). This clearly distinguishes it from sibling bot-instance tools (status, diag, leave-chat) and chat-message tools (ethora-chats-message-v2), so an agent can select it without opening any other schema.

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 gives actionable usage guidance: "Omit roomJid to fan out to every room the BotInstance is in" explains the targeted-vs-broadcast decision, and "Requires the ai-service to be running" states a prerequisite. However, it does not explicitly name alternatives or say when not to use this tool versus ethora-chats-message-v2 or other bot-instance tools, so it misses the top bar for explicit exclusion routing.

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