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

Annotations already mark this as idempotent and non-destructive, but the description adds substantial behavioral context: it returns an approval URL first, produces no change until human approval, refuses to send credentials or authorize actions, and requires identical requestId/details for result retrieval. This goes well beyond the structured metadata and gives an agent an accurate mental model of the tool's side-effect and async behavior.

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?

Four dense sentences with no filler. The primary action is front-loaded, followed by important constraints and the retrieval pattern. Every sentence earns its place.

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?

The description covers the essential lifecycle: send message, receive approval URL, no change until human approval, retrieve result with the same requestId/details. Optional parameters like route, locale, and conversationId remain undocumented, but the presence of an output schema reduces the need to explain return values.

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 requestId ('reuse the identical requestId') and attachmentId ('already-uploaded owned attachment'), and the tool's purpose implies message content. However, route, locale, and conversationId are left entirely to the schema with no added semantics, so compensation is only partial.

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 specific action and resource: 'Send a message to the AurasPay support assistant/provider.' This makes the core purpose immediately identifiable. It does not explicitly differentiate itself from sibling tools like auraspay_ticket_reply or auraspay_assistant_conversation, but the wording is specific enough to distinguish the general intent.

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 clear contextual guidance: an already-uploaded owned attachment may be included, private credentials must not be sent, and no action is authorized until separate human approval. It also explains that the same requestId and details should be reused to retrieve the result. It does not name sibling alternatives or provide explicit when-not-to-use exclusions, but the conditions are clear.

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