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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety/read profile is covered. The description adds genuinely non-derivable context: the output is a signed portable artifact and ALLOW conveys policy, not wallet authority. It omits auth prerequisites, failure modes, and the fact that the artifact is meant to be carried downstream.

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?

Three short sentences with the invocation timing front-loaded and zero filler. Every clause adds information an agent needs (when to call, what it returns, how to interpret ALLOW).

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?

No output schema exists, and the description partially compensates by characterizing the returned artifact and ALLOW semantics. However, for a 2-parameter tool with nested objects and 0% schema documentation, the description leaves the entire input contract unexplained, which is a real gap for correct invocation.

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 0% and the two required parameters are nested objects with constrained fields (kind const STAKE, protocol const lido-steth-submit, policy sub-fields), yet the description explains none of them. 'Strict policy' only faintly gestures at the policy object; action fields like staker, network, input_asset and max_amount_wei are undocumented anywhere.

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 ('preflight'/call before) and resource (ETH staking to Lido stETH) and what it returns ('a signed portable staking artifact'). It implicitly distinguishes itself from the inspect_/observe_ siblings by prescribing use before wallet submission, though it never names those alternatives.

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?

Gives explicit timing guidance ('Call BEFORE an agent asks its wallet to submit ETH to Lido stETH') and clarifies the meaning of an ALLOW result ('policy only, never wallet authority'). It stops short of naming which sibling to use instead when the agent is inspecting or verifying rather than preflighting.

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