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

Annotations only supply readOnlyHint, so the description carries the behavioral load and does so richly: units (AMOUNTS ARE IN MILLIONS OF USD with a worked example), a data hazard (component AND Total rows double-count when summed), the rate/cap profile (limit default 120, hard cap 360, series only), and failure behavior (unreachable store refused as DATA_UNAVAILABLE). This is precisely the context annotations cannot convey.

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?

Purpose and mode selection are front-loaded, and nearly every clause carries operational weight. The dense ALL-CAPS emphasis and the $28 trillion example make it feel packed, but the information density is justified rather than padded.

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 still discloses the return shape ({summary, rows}), the unit convention, and the summing pitfall. Combined with the mode rules and error code, an agent has everything needed to call and interpret this tool correctly.

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, but the description adds genuine meaning beyond the schema: the two-vs-zero argument modes, the refusal of a lone argument, and the series-only scope of limit. That is more than restating the field docs, though some overlap with the schema's 'Sent only together with...' text remains.

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+resource: 'US Treasury debt composition from the Monthly Statement of the Public Debt.' It explicitly names a sibling ('Sibling of get_yield_curve') and its source, so an agent can distinguish it from the other Treasury-adjacent tools without opening a 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 explicit conditional routing: 'Omit BOTH args for the newest month's full class breakdown; pass security_type AND security_class together for that one class's monthly history (only one of them is refused).' Both the when and the when-not (partial pairing refused) are stated, leaving nothing to inference.

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