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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description meaningfully adds beyond them: transient processing with no storage/logging/retention, deterministic execution, and export of an AP2 artifact carrying execution_hash for chain provenance. It stops short of disclosing failure modes or determinism guarantees for the server vs browser paths, so 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 first resources are explained early, but the passage is dense with infrastructure jargon and appends a long FV-status URL and a 64-hex receipt hash that do not help an agent decide or call the tool. The core disclosure sentences (transient processing, AP2 export) earn their place; the trailing receipt pointer does not.

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?

An output schema exists, so return values need not be explained, and the read-only annotations plus provenance notes cover the safety story. The gap is the decision inputs: for a calculator, an agent still needs the policy_parameters field names, which are delegated to an external manifest rather than described here.

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 the purpose of policy_parameters; that sets the baseline at 3. The description does not name any actual policy_parameters fields (it defers to 'the tool's manifest'), so it adds little parameter meaning beyond the schema.

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 name/title state a specific verb+resource (calculate repo haircut) and the description identifies it as an OpenChainGraph compute node in the collateral_mandate family, plus names the downstream tools it feeds (505-tokenized-collateral-eligibility-checker, 506-onchain-cash-leg-finality-checker). However, the body spends most of its words on compute-routing and provenance mechanics rather than on what the haircut calculation actually is, so differentiation from near-name siblings like compute_stock_token_collateral_haircut or compute_basel_haircut_adjusted_exposure rests mostly on the name.

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 states a data-handling rule ('Use synthetic or anonymised inputs only') and explains compute-mode routing, but gives no guidance on when to choose this tool over the many similar collateral/haircut siblings. No prerequisites, no when-not-to-use, no alternative routing.

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