Position Sizing Advisor

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

The description goes well beyond the annotations by explicitly stating 'Read-only: it changes nothing, it only proposes,' which directly addresses the readOnlyHint. It also discloses the data sources (account balance, exchange specs, walk-forward validation over ~9 years) and the underlying sizing logic (leverage cancels out, uses minimum leverage). This provides deep behavioral insight that annotations alone do not offer.

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?

The description is thorough but verbose. The first sentence is a strong front-loaded summary, but the long leverage-explanation paragraph could be condensed. Every sentence provides some value though, so it is not wasteful, but the overall length reduces the conciseness score.

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 an output schema present, the description need not detail return values. It provides enough context about inputs (none) and the reasoning methodology to make the tool's behavior understandable. It lacks details about error cases (e.g., no connected account), but that is not critical for the main usage.

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?

There are zero parameters, so the baseline is 4 per the rubric. The description explains what the tool does without any parameter details, which is appropriate; no additional parameter semantics are needed or added.

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 uses a specific verb 'recommend' and identifies the resource ('how to size trading') with clear scope: risk per trade, number of positions, leverage, margin mode, and notional cap. It is immediately clear what the tool does and distinguishes itself from siblings like top_setups or open_with_bracket by focusing on advisory sizing calculations.

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 provides clear context for when to use the tool: to get position sizing recommendations based on the connected account and market specs. It does not explicitly state when NOT to use it or mention alternatives, but the read-only, advisory nature is explicit, so an agent can infer it is for planning rather than execution. This meets 'clear context, no exclusions'.

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