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

Annotations only declare readOnlyHint, so the description carries the real behavioral load: empty-result semantics, refusal on unreachable store, look-ahead-safe filing-date windowing, that caveats ride in tool_notes, and that the source is free SEC EDGAR Form 4 data. None of this is derivable from the annotations or 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?

Front-loaded with the value proposition and grain routing, then the return shape, then caveats. Dense with capitalized emphasis, which is slightly noisy, but nearly every clause carries information the agent needs.

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?

No output schema exists, yet the description fully specifies the return envelope ({summary, count, events, grain, since_days, limit}), the per-event fields, and the empty/error cases. Nothing an agent needs to call or interpret this tool is missing.

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 already 100%, but the description adds semantic routing that the schema does not: which grain each parameter selects, that omitting both triggers the market-wide scan, and how defaults shift per grain (one row per ticker and direction for market-wide). This goes beyond the structured field text.

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?

States a specific verb and resource ('scan for ACTIVE multi-insider cluster-buy/sell signals') and immediately scopes it as distinct-actor Form 4 clusters with statistical strength. It is clearly differentiated from siblings like ol_insider_recent_buys and get_insider_activity by emphasizing multi-actor clusters rather than individual trades.

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?

Explicitly enumerates the three invocation modes (pass `tickers` for a watchlist, a single `ticker`, or neither for market-wide) and states the alternative relationship between `ticker` and `tickers`. It also tells the agent how to read an empty result ('absence is not a signal') and what happens on failure (store unreachable is REFUSED).

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