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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds real behavioral context beyond them: the 2-business-day SEC reporting lag, which form types populate the data, the fact that SEC transaction codes are decoded, and that a buy/sell summary is produced. It does not address result ordering/pagination beyond the limit parameter, which keeps it short of a 5.

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?

Three sentences, front-loaded with the data type and immediately followed by scope exclusions — the most decision-relevant content comes first. The SEC code enumeration (P/S/M/F/A) is the longest clause and is arguably more than an agent needs to select the tool, but it does describe output content rather than pad the text.

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 carries the burden of describing returns, and it does so by naming the decoded transaction codes and the buy/sell summary. Coverage of scope boundaries is thorough; the only soft spot is that 'recent' is never quantified beyond the limit parameter's 'most recent transactions' wording.

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 50%: 'limit' is fully documented in the schema as the count of most recent transactions, but 'ticker' has no schema description and the description does not state its expected format (e.g. 'AAPL' vs 'AAPL.US'). The description implies the result set is the most recent N transactions but adds no format or validation detail for either parameter, so it neither compensates for the gap nor repeats the schema.

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 insider transactions — officers, directors, and >10% owners buying or selling their own company's stock') and pins the scope to Forms 3/4/5. It also explicitly names the sibling it is not (institutional_ownership for 13F) and the adjacent filing types it excludes (13D/13G), so an agent can separate it from nearby tools without opening a 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?

Gives explicit when-to-use (insider Forms 3/4/5 activity) and explicit when-not (13F institutional holdings → institutional_ownership; >5% beneficial ownership → not covered). The routing condition is stated in the description itself rather than inferred from sibling names.

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