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

With no annotations, the description bears the full load. It does disclose a meaningful behavioral trait — each series is cross-checked against a second copy — which signals reliability the agent could not otherwise infer. It omits, however, the return shape, whether year bounds are inclusive, and any auth or rate-limit context.

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 short sentences, front-loaded with purpose, followed by the subject list and the discovery hint. The series catalog is long but earns its space as an implicit value list; nothing is filler.

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 three-param, no-annotation, no-output-schema tool the description covers what the data is, where it comes from, and how to discover ids. The remaining gap is the year-range semantics and the returned structure, which an agent would have to infer.

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 coverage is only 33%: series has an inline example, but from_year and to_year are undocumented in the schema. The description partially compensates by enumerating candidate series and framing results as 'by year', yet it never explains the range semantics of the two integer parameters.

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-resource pair: retrieve official data series by year, drawn from the publishing agencies. The enumerated series (unemployment, GDP, CO2, exchange rates) makes the domain concrete enough to distinguish it from siblings like get_year_facts or get_timeline.

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?

'Omit series to list them' is a genuinely useful discovery instruction, telling the agent how to enumerate valid ids. However, there is no guidance on when to prefer this tool over get_year_facts, get_timeline, or check_claim, and no preconditions are stated.

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