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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real context beyond them: it performs *independent* inspection against canonical chain data, checks finalized-head finality, and clarifies "OCD never stakes ETH," which tells the agent this tool has no staking side effects. It still omits failure modes (e.g., unfinalized tx, reorgs) and any auth/rate-limit notes.

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?

Two dense sentences with no filler; the inspection target and the non-staking guarantee are front-loaded. The enumerated list of checked items is information-dense but earns its place. Slightly packed for a single clause chain, but not padded.

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 implying return content, and it does by naming exactly what is inspected (Submitted event, sender/value, shares, finality). No completion-time caveats (pending tx, mismatched artifact) are mentioned, which is the main remaining gap.

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 artifact parameter is an untyped empty schema, so the description must carry the load — and it does: the artifact is a *signed OCD staking preflight artifact* and the other input is an Ethereum transaction hash. That is meaningful disambiguation the schema does not 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?

States a specific verb and resource: independently inspects the canonical Lido Submitted event, transaction sender/value, minted shares, and finalized-head finality. An agent can tell it is a read-only chain observation tool. It never explicitly distinguishes itself from the sibling inspect_staking or preflight_staking, so it falls short of a 5.

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 prerequisite is implied by "Given a signed OCD staking preflight artifact and Ethereum transaction hash," which tells the agent what inputs the workflow expects. However, there is no explicit statement of when to choose this over inspect_staking, verify_receipt, or the other observe_* siblings, so the usage boundary is only inferred.

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