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

Annotations only provide readOnlyHint=true, but the description adds real behavioral context: units (millions USD with a worked example), the component-plus-Total row trap that causes double-counting, the limit default/cap, and an explicit DATA_UNAVAILABLE refusal mode. These are exactly the traits annotations cannot convey, so this is well above baseline. Not a 5 only because return-format details (keys, ordering) remain thin, since no output schema exists to fill the gap.

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 the purpose, then the argument logic, then units and caveats in priority order; every sentence carries information. The all-caps emphasis on IGNORED, REFUSED, AMOUNTS, and FREE is slightly noisy, costing it the top mark, but nothing is padding.

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 3-param, zero-required read tool with no output schema, the description covers everything needed: the return shape ({summary, rows}), the double-count hazard, units, the limit cap, a failure mode, licensing, and where caveats live. 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 per-parameter descriptions already define limit and the security fields, giving a baseline of 3. The description adds value beyond the schema by explaining the interaction rule between security_type and security_class and by clarifying the '_' sentinel for Total rows and that limit applies only to series mode.

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 and source: 'US Treasury debt composition from the Monthly Statement of the Public Debt.' It also distinguishes itself from the overlapping sibling by naming get_yield_curve, so an agent can separate the two without opening schemas.

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 explicit branching rules: omit both args for the newest month's full breakdown, pass security_type AND security_class together for a single class's history, and warns that passing only one is IGNORED. This is when-to-use guidance tied directly to argument combinations, not just a vague context hint.

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