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

Beyond the annotations, the description discloses the conditional return contract (transactionBase64 only when safe, structured blocked diagnostics otherwise), the 'do not call finalize' guard, the paid-builder prerequisite, and the signer boundary that hosted builders never receive keypair bytes. These are material behavioral facts absent from the 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 core purpose is front-loaded in a dense, clear sentence, and the execution guidance is organized with labeled sections. The guidance paragraph is longer than strictly necessary and partially restates the schema description text, so it is not maximally lean.

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 paid, state-changing builder with 9 parameters and an output schema, the description covers the full call contract: prerequisites, conditional return behavior, routing/estimation, and key handling. Nothing needed to decide whether to call it or what to do with the result is 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 coverage is 100%, so the baseline is 3; the schema already documents each parameter's meaning. The description reinforces the skip behavior for stopLossPriceUsd and takeProfitPriceUsd and the overall safety gates, but it does not add parameter-level semantics beyond what the schema property descriptions provide.

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 first sentence names a specific verb ('Build ... unsigned transaction'), the resource (a perp position package), and the atomic combined scope (open + stop loss + take profit). This clearly separates it from the many single-purpose sap_adrena_build_* siblings such as open_long or set_stop_loss.

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 gives clear context: use it for an atomic open+SL+TP package and only after policy, balance, oracle-readiness, and simulation checks pass. It also explains the paid-call routing, estimation, and local finalization flow. It stops short of explicitly naming alternative sibling tools and when to prefer them instead.

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