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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds useful behavior: each event is a dated sentence carrying its SEC form, filing date, and link, with closures and launches ordered first. The note that 'matching is the whole count' clarifies that limit does not affect the reported total. Return format is described but pagination beyond limit is not addressed.

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?

Content is front-loaded — source, coverage, and event taxonomy come before parameter behavior. The middle sentences are dense and somewhat run-on (parenthetical definitions plus multiple filters in one clause), but no sentence is padding.

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 read-only, four-parameter, no-output-schema tool, the description covers source, event taxonomy, defaults, filtering, ordering, response shape, and the freshness fields an agent needs to reason about staleness. Minor gap: it doesn't say what an empty day or a non-matching ticker returns.

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 25% (only date is described in-schema), so the description must compensate, and it does: it supplies the YYYY-MM-DD format and default for date, the filter semantics for kind and ticker, and the bounds and default for limit (1–100, default 25). Only the kind enum values themselves are left entirely to the schema.

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 names a specific verb and resource ('ETF news for one day from ETFIQ's ETF News, read from SEC filings') and enumerates the exact event types covered: launches, closures, filings not yet trading, name/ticker changes, fee changes, splits. That granularity clearly separates it from siblings like etf_flows, etf_movers, or etf_profile.

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?

It states the default behavior (latest published day, with is_latest and lag_days signaling staleness) and how to pivot to an earlier day via date, narrow to one kind via kind, or focus on one fund via ticker. It does not explicitly name a sibling to use instead for historical series or flow data, so it stops short of full when-not guidance.

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