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

Annotations already declare readOnlyHint, idempotentHint, non-destructive behavior, and closed-world scope, so the description does not need to establish safety. The description adds useful behavioral context: results are already USD-valued, countsByType covers everything detected before the list was capped, and omitting period scans all time. It does not fully describe pagination or output shape, which is the main remaining gap.

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 description is front-loaded with the core purpose, then usage cues, window guidance, and sibling disambiguation. Every sentence contributes something useful, and there is no 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?

For a read-only tool with two optional, fully documented parameters and no output schema, the description supplies enough context: what events are returned, how they are valued and ranked, the capping behavior, and which sibling tools to use for totals. Nothing essential for correct invocation appears to be 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 description coverage is 100%, so both period and profile are already well documented in the schema. The description reinforces that period is intended for short windows and that omitting it scans all time, but this largely restates schema content and does not add meaning for profile. Baseline 3 is appropriate.

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?

The description states a specific verb and resource: it detects and ranks notable changes such as USD flows, allocation shifts, drawdowns, newly seen sources, and reconciliation to-dos. It also explicitly distinguishes itself from get_pnl_overview and get_capital_flow, so an agent can tell what this tool is for without opening the 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?

It gives concrete when-to-use phrases ("what changed", "anything unusual", "notable moves this week") and recommends short windows like last_7d or last_30d. It also names the alternatives to use instead for profit totals or money in/out, making the routing conditions explicit.

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