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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description discloses genuinely useful behaviour: deterministic server-side compute on Workers, the compute:"browser" delegation path, transient processing with no storage or logging, and an AP2 artifact export carrying execution_hash. That materially exceeds what the annotations convey. It stops short of describing failure modes or the cost/latency of browser delegation, so it is not a 5.

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 long and poorly front-loaded: a regulatory deadline, a documentation URL, and an inline FV-status content hash precede any statement of what the tool does, and the actual purpose appears only in the trailing summary. Some content (data handling, compute modes, artifact chaining) earns its place, but the URL, hash, and 2026 deadline are noise for tool selection.

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?

There is no output schema, so the description carries the burden of return values, and it lists them explicitly (applicable_regime, finality_gaps, finality_tier, singleness_verdict, status_asof, etc.). Combined with the chaining information, compute-mode semantics, and data-handling disclosure, an agent has enough to call it correctly. The one gap is the meaning of the nested policy_parameters inputs, left entirely to the schema's empty properties.

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 schema already documents compute, parent_hashes, parent_tool_ids, and policy_parameters, and the baseline is 3. The description reinforces the compute-mode semantics and explains the upstream-artifact role of the parent hashes, but it adds nothing about the seven nested policy_parameters keys (issuer, jurisdiction, governing_law, singleness_test, settlement_asset, transfer_mechanism, finality_designation), which the schema leaves as untyped empty properties.

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 final summary sentence gives a specific verb and resource: it classifies the settlement asset (CBM token, tokenized deposit, stablecoin, e-money token) against named legal-finality regimes and returns a tier plus a singleness verdict. That is far more specific than a tautology. However, the key statement is buried at the end behind compute/provenance boilerplate, and the description never distinguishes this tool from close siblings such as classify_settlement_finality or check_cash_leg_finality.

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?

Usage is only implied through the artifact chain: the description names the upstream artifact it consumes (art-56) and the downstream tools it feeds, which tells an agent where it sits in a workflow. It gives no explicit statement of when to choose this over classify_settlement_finality or check_cash_leg_finality, and the regulatory-deadline note is a timing warning rather than routing guidance.

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