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

The annotations already establish a safe read-only, idempotent profile, but the description adds substantial behavioral context beyond them: values are USD end-of-day marks rather than live quotes, pnl.endValue must not be reported as current value, calls with arguments not accepted by the chosen view are refused, and history over 200 days is evenly sampled with first and latest day kept and a `truncated` flag set. Those are exactly the traits an agent needs to avoid misreporting results.

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 three views are front-loaded before the per-view argument rules and caveats, and essentially every sentence carries operational information. It is dense and long-sentenced, but the density is justified by the six parameters and three modes; little could be removed without losing a constraint.

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?

For a six-parameter, three-mode read tool this is complete: it covers view selection, per-view arguments, truncation/sampling behavior, end-of-day valuation semantics, profile targeting, and redirection to sibling tools, while the existing output schema handles return shape. An agent has everything needed to call it correctly and interpret the result.

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?

With 100% schema coverage the baseline is 3; the description goes further by stating cross-parameter rules the schema cannot express: arguments apply per view, mismatched arguments are refused, `period` omitted means all time, `slim` is recommended unless composition is needed, and `limit` returns that many best AND worst pairs that are 'never summed across quote currencies'. These constraints add real meaning beyond the per-field schema text.

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?

Opens with a specific verb and resource ('Measure how the portfolio performed') and enumerates the three distinct views with their exact contents (realized vs unrealized, daily series, all-time FIFO per pair). It explicitly routes away from siblings get_portfolio, get_trading_activity, and get_movements, so an agent can select it without opening the schema.

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?

Names the condition that selects each view and which arguments apply to each, states that invalid argument/view combinations are refused, and gives explicit alternatives for adjacent needs ('for buy and sell totals use get_trading_activity; for single trades use get_movements'). It even states which tool holds the current value (get_portfolio), leaving nothing to inference.

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