Scenario Analysis

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

Annotations declare readOnlyHint: true, which the description does not contradict. The description adds beneficial behavioral context beyond the annotation by noting the approximation method ('linear delta/vega/theta approximation') and what the output contains ('Estimated P&L under the scenario with per-Greek contributions'). It avoids claiming any side effects not covered by the read-only hint. While not exhaustive, it supplements the annotation with useful technical detail.

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 concise, with a clear introductory sentence, a short list of use cases, and a structured Args section. Every sentence provides essential information—purpose, usage, and parameter details—without redundancy. It is appropriately sized for a tool with 4 parameters, front-loading the core purpose and then detailing parameters in a scannable format.

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?

Given the tool's complexity (4 parameters, 1 required, no output schema, nested examples), the description covers all necessary aspects: input format with full example, parameter explanations, a note on data source (Greeks from another tool), and output description. It provides enough context for an agent to invoke it correctly, including default values implied through examples. Even without an explicit output schema, the description tells what to expect.

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%, and the description fully compensates. It provides a detailed example for the 'positions' parameter, including JSON structure and a note that plain text works for stock-only portfolios. It also explains each parameter's meaning with examples (e.g., 'stock_move_pct: Percent stock price change to simulate (e.g. -5)'). This is far more informative than the schema alone and fully clarifies parameter usage.

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's purpose: 'Run what-if scenario analysis on a portfolio' and describes what it shows ('how portfolio value changes under different market conditions'). It distinguishes itself from siblings by focusing on scenario/P&L analysis, listing specific use cases like 'What-if scenarios' and 'Portfolio P&L under different conditions', which sets it apart from sibling tools that serve other analytical functions.

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 explicitly states when to use it with bullet points: 'Use this tool when the user asks about: - What-if scenarios - Portfolio P&L under different conditions - Price/vol sensitivity'. It also provides a practical prerequisite ('Get option Greeks from get_options_chain first') linking to a sibling tool, effectively guiding the agent on proper workflow. This is actionable guidance.

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