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

Beyond the readOnlyHint annotation, the description discloses determinism ('same inputs always give the same result'), the inference of direction from the stop's side of entry, the local nature of the computation, and how the optional target only affects reward:risk. These are behavioral traits that materially affect how an agent interprets results and call semantics, all provided in the description.

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 sentences, each earning its place: identity and scope, inputs and outputs, then deterministic behavior and direction inference. The most important differentiator ('not a data-provider lookup') is front-loaded. No redundant phrasing or 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 5-parameter calculation tool with an output schema, the description covers the return values, the optional parameter's purpose, the direction inference rule, and the deterministic nature. Nothing essential for correct invocation or interpretation is missing.

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 100%, so the schema already documents each parameter's meaning and units. The description reinforces the inputs but adds little beyond stating that target is used 'only to report reward:risk' and direction is inferred from stop placement. Baseline 3 is appropriate since schema carries the parameter burden and the description adds marginal context.

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 'Fixed-fractional position sizing' and immediately frames it as 'a local calculation, not a data-provider lookup,' which clearly distinguishes it from the sibling data tools. It names specific outputs (units, notional, implied leverage, stop distance, reward:risk) and the direction inference rule, so an agent knows exactly what this tool does and how it differs from siblings.

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 phrase 'a local calculation, not a data-provider lookup' gives an explicit when-not signal: don't use this to fetch external data. The input/output listing implies when to use it (when sizing a position from account size, risk, entry, stop), but no alternative tool is named or a conditional selection guide provided. Context is clear, exclusions are implicit rather than explicit.

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