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

Annotations already declare readOnlyHint=false, idempotentHint=false, and openWorldHint=false, so the mutation profile is covered. The description adds one genuinely useful non-annotation fact — 'Requires an API key' — but says nothing about who receives the message, notification behavior, or whether a message can be edited/retracted.

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?

Two short, front-loaded sentences with no filler, so the purpose lands immediately. The brevity is close to under-specification rather than padding, but nothing wasteful is present.

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?

With no output schema and no parameter documentation, the description should carry more: it never states what a successful send returns, whether the recipient is notified, or what errors occur for an invalid order. For a mutation tool with an undifferentiated 'other party' concept, that is a real gap.

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%, and the description adds no meaning beyond the parameter names: it does not say what 'body' supports (plain text vs markdown, the 4000-char cap, length limits) or what 'order_id' must refer to (an order the caller participates in). The self-explanatory names alone keep this above a 1.

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 gives a specific verb and resource ('Message the other party on an order'), so the agent knows this sends a message tied to a single order. It does not explicitly name the counterpart sibling get_messages, so the read-vs-write split must be inferred from the tool names.

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?

No when-to-use guidance, no prerequisites tied to order state, and no mention of alternatives such as get_messages for reading the thread or open_dispute for escalation. The only implied usage is that an order must exist.

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