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

Beyond the readOnlyHint annotation, it discloses return shape and ordering (NEWEST FIRST), a critical SAMPLING TRAP (limit returns newest N filings, not the whole window, so rows must not be totaled), which fields are derived (totalValue, fallback position label), the data source, and that it is FREE. This is exactly the behavioral context annotations cannot carry.

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?

A single dense paragraph that is front-loaded with purpose before the caveats. Nearly every clause earns its place (sampling trap, derived fields, source), though the density borders on cramped for one block of prose.

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 compensates by enumerating the return object ({summary, since_days, count, buys}) and per-row fields, plus ordering, caps, and the sampling caveat. An agent has everything needed to call and interpret it correctly.

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 100%, so the schema already documents limit, min_value, since_days, and common_only semantics. The description restates defaults and hard caps (30/180, 25/100) rather than adding new parameter meaning, so baseline 3 applies; the sampling-trap note adds context around limit but is not parameter syntax.

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+resource+scope: 'Recent OPEN-MARKET insider PURCHASES (SEC code P)' across ~5.3k tickers, framed as a daily insider screen. It distinguishes itself from siblings by naming ol_insider_cluster_scan and get_insider_activity, so an agent can route without opening schemas.

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 names complementary siblings ('Pairs with ol_insider_cluster_scan and get_insider_activity') but never states the conditions under which to prefer this tool over them or get_insider_activity. The 'daily insider screen' framing implies usage, but there are no explicit when/when-not rules.

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