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

Annotations already cover safety (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar for additional context is lower. The description adds genuinely useful behavioral facts beyond the annotations: results include confidence intervals, the catalog spans 3,000+ indicators, and there is 'No auth — unlimited free.' These details help an agent set expectations without being redundant with the annotations.

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?

Three sentences, no filler. The core purpose is front-loaded, followed by filters, return shape, examples, and the routing instruction. Every sentence earns its place: purpose, filters/output, examples, sibling pointer, and access policy. The 'No auth — unlimited free' note is compact and valuable.

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?

Given the six-parameter schema is fully self-documented and an output schema exists, the description covers everything else an agent needs: what kind of data is returned (time-series with confidence intervals), how to scope it, where to find codes (who.indicator_search), and access constraints. The description is complete for a read-only data-retrieval tool.

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 description coverage is 100%, so the schema already explains all six parameters thoroughly, including enums for sex, integer ranges, and the ISO alpha-3 format. The description mentions 'country (ISO alpha-3)' and 'sex (both sexes, male, or female),' but this largely echoes the schema rather than adding new meaning. It provides example indicator codes, which is helpful for indicator_code but does not compensate for a coverage gap (there is none). Baseline 3 is appropriate.

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 opens with a specific verb+resource: 'Retrieve time-series values for a specific WHO Global Health Observatory indicator.' It names the filters (country ISO alpha-3, year range, sex) and the output shape (numeric values with confidence intervals). It also gives concrete example indicator codes, making the tool's purpose unmistakable and distinguishable from siblings like who.health.indicator_search, which is about finding codes.

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?

The description explicitly routes users to a sibling tool: 'Use who.indicator_search to find indicator codes.' This effectively tells the agent when to use that alternative (when the code is unknown). It implicitly states the primary use case (you already have an indicator code and want its time-series data). It does not enumerate all exclusion cases, but the context is clear enough for an agent to select this tool correctly.

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