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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety bar is low. The description still earns credit by adding the 'Free' cost signal and the pay-only-when-new polling behavior, plus source provenance ('Data from SEC filings'). The 'Not investment advice' line is boilerplate but harmless.

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?

A single front-loaded sentence that leads with the return value and follows with the rationale. The trailing disclaimer is the only fat, and it is short.

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?

With no output schema, the description carries the return contract and does it: a cursor plus a count. It leaves minor gaps, such as what is returned when `since` is omitted, but nothing critical for correct invocation is missing.

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 100% and the `since` parameter already documents that it comes from an earlier answer's next field. The description restates the newer-than comparison but adds no format or error-handling detail, so baseline 3 applies.

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 pair: returns the newest cursor of the SEC events feed plus a count of events newer than a supplied cursor. That is clearly a different job from get_events, though the description never names the sibling to make the contrast explicit.

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 clause 'so a poller pays only when there is something new' implies the intended pattern (cheap poll before an expensive fetch), but it never says when to call this instead of get_events, nor what to do with the count once obtained. Usage is inferable rather than stated.

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