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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, closed world), so the description carries less burden. What it does add is genuinely non-structured behavior: the entitlement requirement ('Growth plan or higher') and the shape of the detailed result (peak/trough/recovery). It omits what the ranking mode returns per item and any note on the default 365-day window.

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 sentence plus a short entitlement clause — nothing wasted and the primary computation is front-loaded. It is slightly telegraphic: the parenthetical '(with peak/trough/recovery)' and the trailing ranking clause are packed together, so the two modes are less legible than they could be.

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 7 all-optional parameters fully covered by the schema and annotations carrying the safety profile, the definition is close to sufficient. The remaining gap is mode selection: nothing in the description explains that omitting `currency` switches to ranking, nor what the tool returns in each mode (no output schema exists to cover that).

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 all seven parameters — including defaults for `from`/`to`/`base`, the `sort` directions, and the `universe` values — are already documented in the schema. The description's 'vs a base' adds nothing beyond that. 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?

The description names the specific analytic result — maximum peak-to-trough decline versus a base, including peak/trough/recovery — and a second mode: a drawdown ranking. That is materially more precise than the title 'Drawdown'. It stops short of a 5 because it is a noun phrase rather than a stated action and it never contrasts itself with the analytics siblings (analyze_volatility, analyze_history), though none of them duplicate this computation.

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 either/or framing ('... or a drawdown ranking') signals two modes, and 'Growth plan or higher' sets a real precondition for calling the tool at all. However, it never says which mode an agent should pick or what triggers ranking; that switch is only discoverable from the schema note on the `currency` parameter ('OMIT to RANK'). No exclusions or alternative tools are named.

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