net_worth

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

Beyond the readOnlyHint annotation, the description discloses key behavioral details: valuation is as-of, holdings use the latest market rate on or before the date, the book's default currency is used, voided transactions are excluded, and end_date is always included as the last row in a series. These go well beyond what annotations provide. No contradiction with annotations exists.

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-organized and front-loaded with the core formula and modes. Each subsequent sentence adds distinct value: valuation semantics, series behavior, alternative tool routing, dashboard correspondence, and parameter details. There is no redundant or filler content.

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 tool has an output schema, so return-value details are covered elsewhere. The description fully covers the calculation semantics, reading behavior, parameter usage, series construction, and when to choose a sibling tool. An agent has everything needed to invoke this tool correctly.

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%, so the description must compensate. It does so thoroughly with an Args section explaining each parameter: end_date as the as-of date with format, start_date as the optional series start, and interval restricted to 'month', 'quarter', or 'year'. This materially clarifies how to use all three parameters, including the series behavior.

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 a precise definition: 'Calculate net worth (assets minus liabilities), as one value or a trajectory.' It clearly distinguishes itself from the sibling balance_sheet by stating that balance_sheet is for the full A = L + E statement with per-account detail, while this tool is 'the headline number and its trend.'

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 explains the two usage modes: 'end_date alone gives one number; add start_date + interval for a series.' It also names the alternative balance_sheet when full statement detail is needed, and notes that the dashboard's trajectory section uses the same calculation, removing ambiguity about when to invoke this tool.

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