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

The annotations already establish read-only, idempotent, non-destructive behavior, and the description adds meaningful context: it states what evidence supports each score, that atlas partners are split into confirmed and possible, that ADV assets are shown only when matched, and that Form D is a self-reported notice rather than a closed round. That last caveat is a useful warning that annotations cannot express and directly affects how the agent should interpret results.

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 core payload is front-loaded and the caveats land well at the end, but the first sentence is a long run-on built from stacked parentheticals and nested clauses that makes the scoring output harder to parse at a glance. A short bulleted breakdown of returned fields would carry the same information more cleanly.

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 carries the full burden of explaining return values, and it does so in detail: scores, evidence and reasoning, lever status, atlas partners, and ADV assets, plus the unclear bucket. The remaining gap is the rubric itself: what a 1 versus a 5 means is not defined, which leaves the agent dependent on the get_distribution_moat_score sibling to interpret scores.

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?

With 100% schema description coverage, the schema already documents all five parameters, including defaults, ranges, and regex. The description only reinforces two behaviors: an empty date returns the latest day, and unsettled filings surface as unclear, which relates to include_unclear. It adds no boundary conditions beyond that baseline.

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 gives a concrete verb and resource: it returns every new SEC Form D notice from a single filing day, filtered to AI companies and scored 1-5 on the Distribution Moat rubric. That clearly separates it from the calc_* and chart/investor siblings. However, it never mentions get_new_raises, which appears to be the closest overlap, so the boundary between the two tools is left implicit.

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?

Usage context is implied by the 'daily read on AI private markets' framing, and two operational rules are stated: leave date empty for the latest day, and unclear filings are listed rather than guessed. There is no explicit when-to-use or when-not-to-use guidance relative to get_new_raises or get_distribution_moat_score.

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