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

Annotations already cover readOnly, idempotent and openWorld, so the bar is lower, but the description adds genuinely useful behavior: figures are in billions of dollars, the data is published statistics available on every tier, and history depth varies by plan. It omits latency/lag behavior and return shape, which are only partly covered by the 'fresh' schema field.

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?

Dense and front-loaded, with the content inventory first and operational notes trailing. It is a single sprawling sentence with several parentheticals, which costs a little readability but wastes no words.

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 carries the burden of explaining returns, and it does so by listing the data blocks returned (gross/net, bills/notes/bonds, cash balance, quarterly rollup, refunding schedule) plus units and tier availability. Minor gaps remain around response structure and how measures keys map to blocks.

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 baseline is 3. The description restates what the schema already says ('measures filters by key, history adds the monthly series') and adds only the unit context (billions) rather than new parameter semantics such as valid measure key families beyond the schema example.

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 concrete resource (monthly US Treasury borrowing) and enumerates its components: marketable debt gross/net split into bills, notes and bonds, the Treasury's cash balance at the Fed, a quarterly rollup, and the refunding schedule. That enumeration distinguishes it in content from yield-oriented siblings like get_treasury_curve, though no sibling is named explicitly.

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?

Usage is only implied: 'measures filters by key, history adds the monthly series' explains how to narrow output, and the tier note says it always answers, but nothing says when to pick this over get_treasury_curve, get_auctions, or get_rates_and_curve. An agent must infer the boundary from the content list alone.

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