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

Annotations only declare readOnlyHint, so the description carries the rest and does so richly: the hard 20-row cap, the dedup of 4/A repeats, the warning to exclude issuerSelfFiled rows from totals, the origin of totalValue, and the isDerivative caveat. It discloses the exact quirks that would otherwise cause wrong answers.

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 load-bearing constraint (20 rows only) is front-loaded in caps before any other detail, and sibling routing is compressed into a single sentence. It is dense and long, but nearly every clause conveys a real behavioral fact rather than filler.

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 fully specifies the return shape (ticker, transactions and every row field), the cap, dedup behavior, and exception handling, plus the source and tier. Nothing an agent needs to call or interpret this correctly 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 100%, establishing a baseline of 3, but the description goes further by restating and stressing the crucial semantics that `days` only filters within the 20 newest rows and 'never reaches past the 20' - a limit that materially changes how an agent sets the parameter. It adds emphasis beyond the schema 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 ('Recent Form 4 insider transactions for one ticker') and immediately distinguishes itself by naming the alternative data sources for market-wide buys, clusters, and activist stakes. An agent can select this over get_activist_stakes or ol_insider_cluster_scan without opening another schema.

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 routes to alternatives: 'Market-wide buys: ol_insider_recent_buys; clusters: ol_insider_cluster_scan; >5% stakes: get_activist_stakes.' It also states the tier prerequisite ('Requires Researcher tier'), which is a real gating condition the agent needs.

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