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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description needn't repeat that. It adds useful behavioral context: authoritative source (FAOSTAT), country coverage (190+), temporal coverage (annual since 2001), and acceptance of multiple ISO country-code formats. Minor note: 'annual data since 2001' slightly conflicts with the schema's start_year minimum of 1961, but this is an ambiguity rather than a direct contradiction.

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 no wasted words. The primary action is front-loaded, followed by source/indicator and then practical invocation details. It avoids repeating schema facts like defaults or bounds, making it both concise and well-structured.

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?

For a simple read-only tool with 3 parameters (1 required), a fully documented schema, and an output schema present, the description covers all remaining essentials: what is returned, the data source, coverage scope, and accepted country-code formats. An agent has everything needed to invoke the 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 description coverage is 100%, so the schema already fully documents country_code, start_year, and end_year with bounds, defaults, and formats. The description adds minor context (accepted ISO formats, data since 2001) but does not substantially expand parameter meaning beyond the schema, hence the baseline 3.

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 and resource: 'Retrieve prevalence of undernourishment (% of population) and count of undernourished people (millions) for any country over time.' It names the exact UN SDG Indicator (2.1.1) and the data source (FAOSTAT), making it easy to distinguish from sibling FAO tools like food_insecurity or food_loss even though those are not named.

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?

Clear context is provided about what the tool returns and its scope (any country, time series, 190+ countries, annual data since 2001), so an agent can tell this is the tool for undernourishment data. It stops short of a 5 because it never explicitly names alternatives or states when NOT to use it, e.g., pointing to faostat.agriculture.food_insecurity for a different SDG indicator.

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