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

Goes beyond the annotations by declaring coverage limits (FY2015 onward) and the failure mode: out-of-range or unreleased statements return found:false with a reason, never an empty list. That tells an agent exactly how to interpret a negative result, which the read-only/idempotent hints do not.

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?

Front-loaded with what the tool returns, then usage examples, then coverage limits and the default case, in five tight sentences. The parenthetical field list is the only dense spot and it and it earns its space.

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?

An output schema is present, so return shape is already covered, and the annotations handle safety. The description fills the remaining gaps: series scope, date basis, coverage window and the not-found semantics. Nothing an agent needs to call it correctly is missing.

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 the argument types and matching rules are already documented. The description adds the combined default behaviour (omit both to get the latest statement) and restates the fiscal-year and basis conventions, which is modest but real value beyond the schema.

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 resource (US federal outlays by budget function from the Treasury Monthly Treasury Statement) with the scope of what each row contains (current month, FY-to-date, prior-year-to-date, statement date, basis). This clearly separates it from siblings like treasury_receipts or treasury_debt, which cover different series.

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 example queries ('net interest outlays FY2026', 'federal spending on defense through August') and a default rule ('Omit fiscal_year/month for the latest statement'). It never names an adjacent sibling such as treasury_receipts or treasury_federal_net_cost and that keeps it short of a 5.

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