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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, so the description is not carrying the safety burden. It adds genuine context beyond them: the as_of clipping that prevents look-ahead bias and a hard 'Max 5000 rows per page' ceiling, which is the kind of operational limit annotations do not express.

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 dense sentences with no filler: scope first, then the kind semantics, then the row-limit constraint. Every clause carries information an agent would otherwise have to infer.

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 5-parameter read-only tool with no output schema, the description plus annotations are nearly sufficient. The one loose end is 'Max 5000 rows per page' when no pagination or offset parameter exists in the schema, so the agent is told a limit without being told how to page past it.

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 40% — start, end and kind have no schema descriptions — and the description compensates well: it supplies the YYYY-MM-DD format for the date bounds, defines both enum values for kind with concrete examples, and explains what as_of clips. It does not say whether 'end' is inclusive or what happens when it is omitted, leaving a residual gap.

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 ('Returns events of one kind between start and end') and then enumerates the two kinds with concrete content examples ('earnings' = company report dates with symbol and timing; 'macro' = CPI, payrolls, FOMC). That enumeration distinguishes it from data-retrieval siblings such as get_macro_vintage or get_bars, which return values rather than event dates.

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 clarifies the two kind values and the point-in-time role of as_of, which implicitly tells the agent when the tool is appropriate. However, it never names an alternative or an exclusion — an agent cannot tell from the description alone whether to reach for this or get_macro_vintage / get_cot for macro-related questions.

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