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

Annotations already declare readOnlyHint=true, and the description reinforces the read-only nature by listing returned fields. It adds useful behavioral context beyond annotations: the rate is governance-set rather than utilisation-based, sGHO is not a lending position/collateral, and deposits/withdrawals are instant with no cooldown. There is 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 front-loaded with scope ('v3 only, Ethereum only') and core return values. The longer explanatory section about what the rate is not is dense but earns its place by preventing conceptual misuse of the data. It is not overly verbose for the amount of semantic context it provides.

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 no output schema, the description carries the burden of explaining return values and does so substantially: it enumerates the vault fields and the user-specific fields. It also provides product context (governance-set rate, non-collateral nature, instant liquidity) that helps an agent interpret results. Minor gaps like unit details or error behavior are acceptable given the read-only nature.

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 the baseline applies. The description adds some extra meaning for the 'user' parameter—clarifying it returns shares, GHO value, wallet balance, and maxDeposit/maxWithdraw—but the schema already conveys the core semantics ('to include its position'). The version parameter is fully documented in the schema, so no further compensation is needed.

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 a specific resource (sGHO savings vault), states the verb ('Returns'), and enumerates the exact returned fields (targetRatePct, totalAssets, supplyCap, paused flag). It also scopes the tool to 'v3 only, Ethereum only', which makes its purpose unambiguous and distinguishes it from unrelated vault-like tools.

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 clearly implies when to use the tool (when vault state or a user's sGHO position is needed) and gives parameter-level guidance ('pass user to add...'). However, it never names an alternative tool or states when NOT to use this one, despite siblings like get_sgho_preview and prepare_sgho_action existing. Usage context is present but exclusions are absent.

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