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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, and the description goes well beyond them: the vintage floor rule, that a stale country is dropped rather than scored 0, the concrete UK example, and what each metric actually measures ('intentional killings only, not petty crime or road deaths'; population-weighted PM2.5). It even discloses that the disclaimer leads every response.

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?

The two operational modes are front-loaded and each sentence carries information (sources, floor rule, example, metric definitions). It is dense and slightly overstuffed with the closing disclaimer/liability sentence, which is a mild cost against an otherwise efficient structure.

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 an output schema, annotations covering the safety profile, and 100% schema coverage, the description fills every remaining gap an agent needs: when countries are dropped, what the metrics mean, and how the two modes behave. Nothing required 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 schema carries the parameter syntax (baseline 3). The description still adds real meaning beyond it: the ranking is over the '41-country spine', default direction is lowest-first, and it clarifies the two-mode split between `countries` and `metric`/`sort`/`limit`.

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 (returns side by side / ranks) with concrete resources: intentional homicides per 100,000, PM2.5 exposure, and INFORM disaster-risk score and band. The framing 'Measured danger once there' plus the named data sources distinguish it from siblings like compare_country_risk or compare_climate 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?

Explicitly branches usage: pass `countries` (two or more ISO alpha-2 codes) for a side-by-side comparison, omit it to get a ranking by one metric. That is clear context for both modes, but no sibling alternative is ever named (e.g. compare_country_risk), so the 'vs alternatives' half is left to inference.

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