draft_order

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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=true. The description correctly adds the important behavioral fact that no real trade occurs and that a human CLI confirmation step is required — real value beyond the annotations. It doesn't explain what happens on repeated calls or what the returned object contains (though an output schema exists).

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 short sentences, front-loaded with the core action and followed by the two safety-relevant caveats. No wasted wording, though the phrasing is terse to the point of omitting parameter guidance.

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 write-adjacent financial tool with an output schema and annotations, the description covers the critical safety story (simulated, no execution, human confirmation). However, with 0% schema coverage across 5 parameters, it leaves the agent without guidance on side values, order_type defaults, or limit_price conditions.

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% — none of the 5 parameters have descriptions. The description mentions none of them; it doesn't clarify that side is buy/sell, that order_type defaults to market, or that limit_price is only relevant for limit orders. That relationship between order_type and limit_price is a real semantic gap the description should have closed.

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+resource: it generates a simulated order left in PENDING_CONFIRMATION state. It also distinguishes itself from real trading by explicitly saying no real transaction is executed. It doesn't differentiate itself from siblings like get_quote or portfolio_risk, but those are read-only data tools so the distinction is implicit.

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 implies when to use it (when a user wants a draft/mock order without executing a trade) and adds the critical note that the user must confirm manually in the local CLI. It doesn't state exclusions or name alternatives, so guidance is implied rather than explicit.

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