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

No annotations are provided, so the description carries the full behavioral disclosure burden. It does disclose a key limitation (up to 2,000 rows), the two distinct modes, and the fields returned. It does not mention rate limits, data latency, or specific output formatting. For a read-only data retrieval tool, this is adequate but not comprehensive, so a score of 3 is appropriate.

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 description is a single, dense sentence that packs a lot of information without unnecessary fluff. It front-loads the core purpose, then details the two modes. While it is somewhat long, it is efficiently structured and every clause adds meaning. It earns a 4 for being concise and well-organized, though not perfectly minimal.

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?

Given there is no output schema, the description must convey what the tool returns; it does list the fields (insider name, title, transaction code, shares, price, value, date) and the row limit. It also explains the two call modes with their parameters. It does not explicitly state the exact output format (e.g., JSON array) or mention error cases, but for a data retrieval tool this is reasonably complete. The presence of 6 parameters and two modes is handled well, so a 4 is justified.

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 83% (5 of 6 params have descriptions; 'window' has an enum but no description). The tool description adds value by explaining the dual-mode usage: from/to/limit for ticker history, type for latest view, and ticker for both. It clarifies that type is only for the latest view (likely filtering buys/sells) and that limit defaults to 200. This goes beyond the schema, which already describes each parameter but does not tie them together into a coherent usage model. Thus, the description enriches parameter semantics significantly.

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 clearly states it retrieves insider transactions from SEC Form 4 and lists the fields returned (insider name, title, transaction code, shares, price, value, date). It also distinguishes two usage modes: ticker history and latest trades across companies, which separates it from sibling tools like insider_clusters or planned_insider_sales. The purpose is specific and unambiguous, though it does not explicitly name alternatives, so it is not a 5.

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 provides clear guidance on when to use each mode: 'History for a ticker (from, to and limit select the window...)' and 'latest trades across companies (type buys for open-market purchases, sells for sales)'. However, it does not mention exclusions or alternatives beyond that, such as when to prefer insider_clusters over this tool. Implied usage is clear, but explicit when-not-to-use guidance is missing.

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