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

With no annotations, the description carries the full behavioral burden and does cover the two things an agent most needs: this is a paid call at $0.10 USDC on Base, and no account or API key is required. It also discloses provenance ("as filed" SEC Form 4). It stops short of stating whether the response covers all history or a recent window, and says nothing about the returned row shape despite there being no output schema.

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?

Very compact and front-loaded — "Paid" first, then what the data is, then cost, then access, then endpoint. Every clause carries information the agent needs. The raw URL at the end is the least necessary element and the fragments read telegraphically rather than as prose, keeping it just short of a 5.

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 one-parameter paid data endpoint the description covers source, scope, cost, and auth, which is most of what is needed. But with no output schema and only a `limit` parameter, the agent cannot tell the time horizon of the data (all filings? recent?) or what fields each row contains, and time scope is material for an insider-trading dataset.

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 100% and the single `limit` parameter is fully documented in the schema ("Rows, 1-100 (default 20)"). The description adds nothing about it, which is acceptable at full coverage but leaves no added meaning. 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?

"RAPP insider BUYS from SEC Form 4" states a specific resource and dataset precisely, with the qualifier "open-market purchases by officers, directors, 10% owners" narrowing exactly which Form 4 transactions count. The ticker in the description and name distinguishes it from the ~40 other buy_insider_* siblings, though it never explicitly names the generic buy_insider tool as the all-tickers alternative.

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 description states cost and access mechanics ("Paid", "$0.10 USDC on Base", "No account, no API key") but gives no when-to-use guidance: nothing says whether this covers a fixed lookback window, whether to prefer generic buy_insider for multi-ticker queries, or how it relates to sibling tools like search_facts. An agent must infer the selection rule entirely from the naming convention.

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