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), yet the description adds real behavioral context: deterministic execution, server-side vs. browser delegation by compute mode and gpu flag, transient processing with no retention or logging, and an AP2 artifact export carrying execution_hash for chain provenance. The 'bre...' truncation and the opaque FV-status receipt add noise rather than transparency.

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 payload opens with redundant boilerplate ('OpenChainGraph compute node (analytics_mandate). Deterministic OpenChainGraph compute node.'), embeds a long provenance URL and a 64-character FV-status hash, and truncates the actual domain summary mid-word at 'bre...'. The informative content is buried rather than front-loaded.

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?

Absent an output schema, the description does enumerate the twelve return fields, which is genuinely useful. But it leaves the pricing inputs (the eight nested policy_parameters keys) unexplained, so an agent knows what comes out yet not what must go in, which is a significant gap for a quantitative modeller.

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 and parent_tool_ids; the description's compute-mode text merely restates the enum. The policy_parameters object's eight fields (opex_pct, reins_pct, premium_pct, loss_ratio_pct, etc.) are undocumented in both places, and the description gives no units, ranges, or defaults for them.

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 Summary sentence states a specific verb and resource: unit economics for embedded insurance attaching per-transaction coverage, and enumerates the computed metrics (GWP, NWP, expected losses, commission, opex, underwriting profit, combined ratio). The purpose is clear once found, but it sits behind generic compute-node boilerplate and never distinguishes itself from adjacent pricing tools such as calculate_claims_stp_economics or compute_mlr_rebate.

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 never says when to choose this tool over a sibling, nor does it set exclusions. The only guidance offered is the privacy constraint 'Use synthetic or anonymised inputs only' and the compute-mode selection rules, which are usage hints rather than tool-selection criteria.

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