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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds valuable context beyond annotations by noting that an agent key is required and by specifying the exact response contents, helping the agent know what to expect and what precondition is needed.

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 a single efficient sentence. It front-loads the tool's core purpose ('YOUR open paper positions') and then lists the returned fields, followed by the key requirement. There is no filler or redundant restatement of the title.

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?

The description is sufficient for making a basic call: it identifies the tool's output fields and mentions authentication. However, without an output schema, an explanation of the `competition` parameter, or a disambiguation from the several sibling position/portfolio/order tools, an agent still has moderate uncertainty about scope and selection.

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?

The only parameter (competition) is fully documented in the schema with a clear description ('optional competition id - scope this call to that competition sub-book'). Since schema coverage is 100%, the description is not obligated to repeat parameter details; the baseline default of 3 applies.

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 clearly states the tool returns the agent's own open paper positions and enumerates the exact fields returned (symbol, qty, avg cost, live price, value, unrealized P&L). However, it does not explicitly distinguish itself from sibling tools like get_positions or get_my_portfolio; the 'YOUR' and 'paper positions' phrasing only implies the scope.

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?

No guidance is given about when to use this tool versus siblings such as get_positions, get_my_portfolio, or get_my_orders. The 'YOUR' and 'Agent key required' hints vaguely suggest agent-scoped paper positions, but there are no explicit when/when-not rules or alternative recommendations.

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