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

Annotations already set destructiveHint=true and readOnlyHint=false; the description adds the modeling approach (converging rebalance swaps) and 'hard rule 1' that the non-custodial pipeline only rotates spot holdings. This provides behavioral context beyond the flags without contradicting them, though it doesn't disclose what a destructive operation would do in this context. The 'never deposits externally' constraint is a valuable behavioral caveat not inferable from 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 packed but each sentence serves a purpose: a clear one-liner, modeling rationale with the hard rule, and a pointer for optional params. The density is appropriate for an expert-facing tool, though it's denser than average and the 'hard rule 1' introduction is slightly cryptic without prior context.

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 presence of an output schema (no need to document returns) and annotations covering side-effect flags, the description covers purpose, modeling, constraints, and parameter grouping. The only minor gap is the lack of explicit prerequisites for wallet_address or an example allocation format, but the sibling references and hard rule give an agent enough to proceed correctly.

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 schema description coverage at 0%, the description compensates by grouping direction_mode/allow_short/regime_override as a 'deterministic signal' and pointing to strategy_dca_create. It also signals 'target basket allocation' for target_allocation and implies config params mirror strategy_rebalance_create. However, individual parameters like risk, slippage_bps, and interval_seconds are left to the sibling reference, giving no direct semantics for several fields.

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 'Create' + resource 'yield-farm strategy' and differentiates from siblings strategy_rebalance_create and strategy_dca_create. The modeling distinction (external yield protocol has no analogue) further distinguishes it. A clear, unambiguous purpose with sibling references.

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?

References sibling tools strategy_rebalance_create (shared executor/config) and strategy_dca_create (direction params), giving clear context on relationships. However, it stops short of an explicit when-to-use versus strategy_rebalance_create beyond the modeling rationale, relying on the 'hard rule' for clarity. This is clear context with implied but not exhaustive exclusions.

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