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

It discloses a lot of behavioral context: bounded coverage, a three-row cap applied after filtering, grouped identical rows, matchingStoredRows not being a transaction count, source links per row, and the semantic nature of each category (fund changes are reported holdings, influencer posts are commentary, trader positions are derivatives, government awards lack direction). It never states auth or rate-limit requirements, and the read-only/open-world profile is already covered by annotations, so this lands above baseline without being exhaustive.

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?

Roughly seven packed sentences with no filler, and the most decision-relevant facts (what it covers, filter semantics, ticker omission behavior) come first. Later sentences are telegraphic to the point of terseness (e.g., 'Category congress covers politicians'), but nothing 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?

With no output schema, the description must describe returns, and it does: bounded discovery preview vs ticker-scoped research, three-row cap, per-row source links, grouped identical rows, and the caveat about matchingStoredRows. For a four-parameter read tool this is complete enough to call correctly without opening anything else.

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 description coverage is 0%, so the description must carry the meaning: it explains activity values (buy/adding/accumulating, sell/reducing, all), maps 'congress' to politicians, gives example actor strings (Pelosi, Berkshire), and explains ticker omission vs presence. However 'funds', 'insiders', 'gov-contracts', 'influencers', 'top-traders' enum values and the ticker pattern itself are not explained, so the coverage is partial.

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 concrete resource (smart-money activity: buys, sells, holdings, statements) and enumerates the covered actor classes (Congress, insiders, funds, influencers, top traders). It implicitly differentiates from siblings by ruling out 'market-wide convergence ranking' (pointing away from get_smart_money_overlap), though it never names the alternative directly and the opening verb is buried in a long enumeration.

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 gives explicit conditional behavior: omitting the ticker yields a discovery preview, supplying one yields security research, and activity/category filters narrow results before the three-row cap. What's missing is an explicit 'use X instead when...' pointer to a named sibling, leaving the convergence-ranking exclusion as the only routing hint.

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