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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds genuine context beyond those: deterministic compute, transient processing with no storage/logging/retention, a 'synthetic or anonymised inputs only' constraint, and that it exports an AP2 artifact carrying execution_hash. That data-handling and provenance disclosure is real added value; it stops short of 5 only because the actual reconciliation behavior is undisclosed.

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 passage is dominated by framework boilerplate, an external URL, a long FV-status hash, and an offline-verification note that do nothing to help tool selection. The actual purpose is neither front-loaded nor elaborated; signal-to-noise is poor.

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 an output schema present the return values needn't be explained, and the data-handling/provenance disclosure is adequate. However, for a reconciliation tool the description never states what is reconciled or when it applies, leaving the core selection question unanswered.

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. The description's compute-mode explanation largely duplicates the schema, and policy_parameters remains an opaque manifest lookup in both places. Baseline 3 is appropriate when the schema does the heavy lifting.

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 first sentence merely restates the name and title ('x402 V2 Batch-Settlement Reconciler: OpenChainGraph compute node (settlement_mandate)') rather than explaining what the reconciliation actually does. An agent learns it is a 'deterministic compute node' but not what inputs it reconciles (batches? mandates? settlement legs?) or what the decision function decides. The specific verb+resource is present but the meaning is essentially tautological against the title.

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 compute:'auto'/'browser' guidance describes the framework's execution model, not when this tool should be chosen over the many sibling reconciliation tools (e.g. reconcile_mpp_subscription, check_x402_domain_nonce_window, model_x402_settlement). No when/when-not, no dependency prerequisites beyond the upstream/downstream artifact names.

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