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

Annotations already declare read-only, idempotent, non-destructive behavior, but the description adds substantial non-obvious context: the return contents (ranges by operating denominator and period, evidence paths, concentrations, unknowns) and the important caveat that chained percentages and shock impacts are estimates, never stock-return predictions. The requirement that custom transmission assumptions be explicit is a genuinely useful behavioral disclosure.

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?

Four sentences, each carrying distinct weight, with the core action front-loaded before outputs, caveats, and tier limits. Dense but not padded; minor cost is that the tier and caveat sentences compete for attention.

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?

With no output schema, the description covers return values well and discloses the estimate-vs-prediction caveat and tier caps. It is thin on the heavily nested scenario/transmission structure, so the schema's deepest inputs still require inference, but the practical calling picture is largely complete.

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% for a 4-parameter tool with deeply nested objects, so the description must compensate. It explains that weights are signed NAV fractions and that depth maps to hops, but says nothing about cashWeight, the changeBps vs changePct distinction, or the transmission object's basis/factor/exposurePct fields, all of which are undocumented elsewhere.

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?

States a specific verb ('Apply ... shocks') and resource ('weighted holdings'), and enumerates the shock dimensions (country, commodity, rates, FX, tariff, supplier, customer) that distinguish it from portfolio.positions and portfolio.performance. An agent can identify the operation 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?

Gives concrete context on tier limits — free preview handles one holding at depth one, Pro supports 100 holdings and four hops — which tells the agent when this tool is viable. It stops short of naming alternative tools or stating when not to use it, so it lacks explicit sibling routing.

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