Portfolio Greeks

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

readOnlyHint already indicates a non-mutating tool, and the description avoids any contradictory action. It adds useful behavioral context like prerequisite data sourcing from get_options_chain, support for plain text stock-only portfolios, and a risk-level assessment in return. It does not disclose edge case behavior or return structure, so not a 5.

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 well-structured and efficient: a one-line summary, explicit use-case bullets, a clear Args section with example, and a Returns line. It is short enough to be understood quickly but contains all essential input prerequisites.

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 covers inputs, prerequisites, and the output category sufficiently for a one-parameter read-only tool. However, since there is no output schema, the Returns line is minimal and does not define the shape or semantics of the risk-level assessment or aggregated Greeks.

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 schema provides only a string named 'positions' with zero coverage. The description largely compensates by explaining the expected JSON array, providing a concrete example, documenting fields such as ticker, position_type, quantity, current_price, strike, expiration, delta, theta, and vega, and noting that plain text works for stock-only inputs.

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 specifies the verb and resource: aggregate Greeks for a portfolio of positions, specifically net delta/theta/vega plus risk-level assessment. It differentiates from sibling tools by focusing on portfolio-level calculation rather than fetching or estimating a single-chain or third-order Greeks.

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 gives explicit user-intent triggers such as Portfolio Greeks, Net delta/theta/vega, and Position exposure. It also instructs users to get option Greeks from get_options_chain first. However, it does not explicitly mention when-not-to-use or compare against closely related siblings, so it falls short of a 5.

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