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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description contributes beyond that with the data-semantics caveat 'Unavailable years are not zero', which prevents an agent from misreading absent rows as real zeros. It does not mention pagination or result ordering despite limit/offset existing, so it is not fully transparent.

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 compact sentences with the resource scope front-loaded and the exclusion list immediately after; nothing is repeated or padded. The middle exclusion sentence is slightly list-like and its phrasing ('language', 'individual voting') is terse enough to be ambiguous. Overall efficient and well-ordered.

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?

There is no output schema and no annotation covering data shape, so the description is the only source of return-value information, and it does not say what a flow record contains or how results are paged. Five query parameters, including a limit/offset pair, go entirely unexplained. The one caveat it does offer (unavailable years) is helpful but far from sufficient for a five-parameter 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 0%, so the description carries the full burden, and it does not deliver: from_year, to_year, limit, and offset are never explained or even named. Worse, it references a 'receiving-locality label' dimension that has no corresponding parameter in the schema, which can mislead an agent into expecting a locality filter. The only mapping it gives is conceptual (year, country) rather than per-parameter.

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?

Names a specific resource (new-immigration registry flows) and states the dimensions it is organized by (year, country, receiving-locality label), then explicitly excludes sibling domains like current population and individual voting. That exclusion list lets an agent distinguish it from get_birth_country_population and get_demographics without opening the schema. It lacks an explicit verb such as 'return' or 'list', which keeps it short of a 5.

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 'Not current population, language or individual voting' sentence provides when-not guidance by pointing away from adjacent tools, which is genuinely useful routing information. However, it never states the positive condition for choosing this tool over get_birth_country_population or get_demographics, and no sibling is named directly. Usage is implied rather than instructed.

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