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

Annotations already indicate this is a mutating, non-idempotent, potentially destructive operation (readOnlyHint=false, destructiveHint=true). The description adds meaningful behavioral context: it explicitly flags the approximation caveat ('APPROXIMATE: no full per-fill replication (every execution is flagged approximate)') and explains how the wallet's actions are 'sourced each tick.' This goes beyond what annotations provide, though it could also mention side effects or prerequisites. No contradiction with annotations.

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 compact and well-structured: one sentence for purpose, one paragraph for key parameters and the approximation caveat, one line for cross-reference. Every sentence contributes substantive information without redundancy. It is front-loaded with the primary action, making it easy to scan. This is an example of efficient, purpose-driven writing.

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?

Given the tool's complexity (12 parameters, 0% schema coverage), the description covers the central mechanism (mirroring a wallet, approximation) but leaves many parameter semantics to inference or a cross-reference. The presence of an output schema means return values need not be described, but parameter completeness is lacking. It is adequate for a quick understanding but would benefit from expanding on additional parameters or clarifying the reference tool's documentation.

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?

With 0% schema description coverage, the description is responsible for explaining parameters. It does explain tracked_wallet and usd_per_buy, including scaling by size_multiplier, and it points to strategy_dca_create for risk/direction params. However, the remaining eight parameters (e.g., regime_override, interval_seconds, allow_short) are not described, leaving a significant gap. The cross-reference helps but does not fully compensate for the missing parameter documentation.

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 opens with a specific verb+resource: 'Create a copy-wallet strategy -- mirrors a tracked wallet's entries/exits.' This clearly differentiates it from sibling strategy creation tools like strategy_dca_create or strategy_snipe_create, which target different strategy types. The name itself is also descriptive, but the description adds the resource ('copy-wallet strategy') and the precise behavior ('mirrors entries/exits').

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 description implicitly defines when to use the tool: when you want to mirror a wallet's trades. It also provides a cross-reference to strategy_dca_create for risk/direction parameters, which gives a clue about related tools. However, it does not explicitly state alternatives or cases where this tool should NOT be used. Since the purpose is specific and the sibling list is broad, the implied usage is clear but not exhaustively contrasted.

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