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

Annotations declare readOnlyHint, idempotentHint and destructiveHint=false; the description is consistent with a non-committing simulation and adds real context: limits are graded after the recompute, and supplied data needs permission while the flag does not verify a licence. The licence disclaimer is a useful scope caveat the schema cannot express. It does not state any rate, size or runtime limits for the large position/trade caps.

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, both front-loaded with the action and then the two conditional paths. Nothing is repeated from the schema or annotations and no sentence could be dropped without losing information.

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?

An output schema exists, so return values need not be described, and the complex nested request is left to the schema. What remains missing is how data_mode interacts with the omit-request path and what happens when limits or scenarios are omitted, which would matter for a what-if run.

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 carries the burden. It explains the null-request path and the meaning of rights_confirmed (a permission assertion, not licence verification), which is genuinely beyond the schema. The twelve fields inside WhatIfRequest, notably data_mode, confidence, horizon_days and limits, get no added meaning, though their names are largely self-describing.

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 chain and resource: apply proposed trades to a book, recompute exposure, stress and tail, then grade limits. That is unambiguous and clearly a pre-trade simulation, distinct from the sibling analytics tools by name and action.

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?

Gives explicit routing for two cases: omit the request to run the shipped synthetic example, or supply data with rights_confirmed=true. It stops short of saying when a pre-trade what-if is preferable to an existing-book analytics call, but the conditions it does state are actionable.

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