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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety is covered. The description does add genuinely useful behavioral context beyond them: it is free, sourced from FFIEC filings, and labels each output number as filed, derived, or assumed, which tells the agent how much to trust the result. It stops short of describing precision, latency, or failure modes for banks lacking filing history.

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?

A single front-loaded sentence with three compact clauses: what it computes, how it computes it, and how results are labeled. No filler, no repetition of the title, and the most decision-relevant information (the output and its provenance) comes first.

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?

Five parameters with full schema descriptions and a clear read-only profile; the description covers the computation source, the cost, and the confidence labeling of outputs, which is what an agent needs to select and trust the tool. With no output schema, the extra note that results are tagged filed/derived/assumed fills the main remaining gap.

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 coverage is 100%, so baseline is 3, but the description adds a real interpretive layer: 'using its own filed pass-through history' explains what the derived loan/deposit betas are and therefore what the override parameters replace. It does not clarify the regime enum choices or the sign convention on fedMoveBp beyond what the schema already states.

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 names a specific verb and output set ('Estimate how a Fed funds move changes a bank's loan yield, deposit cost, and net interest income') and the mechanism ('its own filed pass-through history'), so the resource is unambiguous. It does not name or contrast against close siblings like margin_capture or deposit_pricing_decision, so an agent must still infer the boundary.

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?

Use context is only implied by the purpose (rate-shock scenario on NII); there is no explicit statement of when to prefer this over margin_capture or loss_reserve_scenario, nor any exclusions. The only directional guidance ('Automatic is right for most uses') lives in the schema, not the description.

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