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

With no annotations supplied, the description carries the full burden. It does disclose real behavior beyond the schema: one row per company, deduplication to the latest filing with a `filings` count, the fact that the response reports the date range actually covered, and a coverage caveat tied to the state filter. It omits the default time window with no params, ordering, result caps/pagination, and any rate-limit or auth notes, leaving meaningful behavioral gaps for a read tool.

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?

The payload is dense and mostly front-loaded: field list first, then row granularity, then coverage behavior. The opening fragment ('US startup fundraises from SEC Form D filings: ...') is slightly telegraphic but no sentence is wasted.

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, so the description must explain return shape — and it does, listing fields and the extra `filings` count. But for a two-parameter, zero-required tool it leaves a key operational question unanswered: what does a bare call return (default window, result volume, sort order), which an agent needs before invoking 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 50% (only `state` is documented in the schema). The description adds genuine meaning to `state` by explaining its effect on coverage (full 14-day), but says nothing about `city` — whether it is matched exactly, requires a state, or narrows the window further — nor about the default when both are omitted.

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 the concrete resource (US startup fundraises from SEC Form D filings) and enumerates the returned fields, so an agent knows exactly what data this yields. It does not differentiate from siblings like get_jobs or get_launches, but those are clearly different resources by name and the tool's own scope is unambiguous.

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 line 'Pass a 2-letter state for full 14-day coverage of that state' implies that omitting state yields narrower coverage, which is implicit usage guidance for the filter. However, there is no explicit when-to-use versus another tool, no statement of what happens with zero parameters, and no prerequisites or exclusions.

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