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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds genuinely new behavioral context: data is 'sourced' (provenance), carries units, notes and update dates, may contain missing values, and estimated/interpolated points must not be used as substitutes. That is meaningful disclosure beyond 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 tight sentences with the returned-data profile front-loaded, followed by the comparison limit and the anti-substitution rule. Each sentence carries content, though 'Never substitute estimated chart points' is terse enough to be slightly cryptic out of context.

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 and 0% schema coverage, the description does well to name return fields. But it leaves gaps an agent needs: what time range is returned, what 'country' accepts relative to 'compare', how missing values are represented, and whether the catalog tool must be called first for metric semantics.

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 0%, so the description must compensate. It clarifies that 'compare' takes a three-letter country code and is capped at two countries, and implies 'country' is analogous, but it never explains the six 'metric' enum values, their units, or the temporal scope of the observations.

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 and resource: 'Read sourced World Bank indicator observations', and enumerates the returned fields (units, notes, update dates, missing values). It implicitly separates itself from read_public_catalog and read_public_civic_records by naming the World Bank indicator domain, but never explicitly contrasts with those siblings.

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?

'Compare at most two three-letter country codes' gives a hard constraint on the comparison path, and 'Never substitute estimated chart points' rules out an anti-pattern. However, there is no explicit guidance on when to use this versus read_public_catalog (e.g., to discover metric names) or what to do when a value is missing.

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