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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower, yet the description still adds real substance: the detection thresholds (2+ directors within 14 days), the four pattern categories, and the alert output shape with severity and total value. It does not disclose latency, null/no-signal behavior, or limits on how many alerts return.

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?

Four compact sentences, front-loaded with the action and resource, then the pattern taxonomy, then the return shape, then usage. Slight redundancy in repeating 'insider'/'conviction' across sentences, but nothing is padding.

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?

An output schema exists, so return values need not be re-explained, and the annotations carry the safety profile. With 100% schema coverage and only two parameters, the description supplies enough for correct invocation; the only real gap is routing guidance relative to the insider-trade siblings.

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 100% – ticker format and the months default (6) and max (24) are all documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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 ('Detect insider conviction cluster patterns for an NZX company') and enumerates exactly what it detects: cluster buys, cluster sells, sustained accumulation, and conviction reversals. That is far more precise than the raw-trade siblings (get_insider_trades, get_insider_ownership), though it never names an alternative explicitly, so it stops short of 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 closing sentence 'Use when investigating whether insiders are acting with conviction' gives a use context, but it largely restates the tool's own purpose. There is no guidance on when NOT to use it and no routing to get_insider_trades, get_insider_ownership, or subscribe_insider_alerts, which is what an agent selecting among ~200 siblings actually needs.

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