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

Annotations only declare non-read-only, non-idempotent, non-destructive. The description adds real behavioral context: reduce-only enforcement, the trigger semantics, and post-trigger execution as an IOC limit bounded at triggerPrice ± slippageBps. It omits auth/permission requirements and what happens if a stop already 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?

Two sentences, front-loaded with the core action, and the dense second sentence carries only necessary execution detail. No filler.

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 mutation tool with no output schema and thin parameter coverage, the description covers the mechanics an agent needs to place the order correctly. Gaps remain around response shape, idempotency/replacement behavior, and the undocumented parameters.

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 coverage is only 17%, so the description must compensate. It meaningfully explains side, triggerPrice, and slippageBps (default 500, raise for thin books), but leaves market, size, and clientId entirely undocumented in both schema and description.

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?

States a specific verb+resource with scope: 'Place a reduce-only Stop loss (conditional market order)'. The reduce-only and conditional-order framing clearly separates it from place_limit_order/place_market_order, though it never names a sibling tool explicitly.

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?

It gives directional usage guidance for the side parameter (SELL closes LONG, BUY closes SHORT), which is genuinely useful. But it offers no when-to-use vs place_take_profit or place_limit_order, and no conditions under which this tool is the wrong choice.

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