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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real value beyond that: vintage/coverage figures (36/41 for doctors-nurses, 31 for beds), source attribution per row, the rule that older figures are omitted rather than served as current, default sort direction, and a disclaimer that every response carries. That is unusually rich behavioral disclosure.

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 but well front-loaded — the core capability opens the sentence and caveats follow. Em-dash heavy and packed, but each clause carries distinct information (sources, caveat, coverage, param behavior, disclaimer) rather than 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?

An output schema exists, so return format need not be explained, and the description doesn't waste space on it. It covers sourcing, coverage limitations, sorting, and the informational-only caveat — enough for an agent to call this correctly. Minor gap: the `limit` parameter's interaction with default sort is left to the schema.

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?

With 60% schema coverage, the description compensates meaningfully: it clarifies that `metric` does not rank (only doctors by default; nurses and beds selectable), that `sort` defaults to highest and `sort=lowest` flips it, and that `country`/`countries` map to single vs side-by-side. It leaves `limit` to the schema, but the enum-bearing parameters are well explained.

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?

It names a specific resource (doctors, nurses, beds per 10,000), the data sources (WHO GHO, OECD), and the companion metric (UHC service-coverage index). This is clearly distinguishable from siblings like compare_healthcare or health_prep because it frames itself as density rather than access. An agent knows exactly what this returns without opening the 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?

It gives a strong limitation cue ('Density is not access... not whether a visitor can use it or what it costs'), which implicitly points to a different tool for access/cost questions. It also explains when to use `country` vs `countries`. But it never names an alternative sibling to route to, so the when-not guidance stops short of explicit redirection.

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