verify_decision

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description doesn't need to restate safety. It adds valuable context beyond annotations: the $0.02 cost, automatic payment from the configured wallet, and the meaning of CHANGED as stale evidence. This exceeds minimal disclosure.

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?

Every sentence carries unique information: purpose, when to call, why it's needed, outcome semantics, cost comparison, and payment behavior. No filler or redundancy despite being a longer paragraph.

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?

For a one-parameter read-only tool, the description fully covers the use case, outcome values (CONFIRMED, CHANGED, INDETERMINATE), cost, and why freshness matters. Even without an output schema, the possible results are explicitly enumerated, making the tool self-sufficient.

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?

The input schema has 100% coverage for decision_id, describing it as issued by attest_price_event. The description only mentions that it comes from someone handing you a decision_id, which aligns with the schema without adding new syntax or format details. Baseline 3 applies since 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 description uses a specific verb ('verify') and resource ('attested settlement'), and clearly states the action: re-resolve against price venues and report CONFIRMED, CHANGED, or INDETERMINATE. It distinguishes itself from sibling tools like resolve_price_event by focusing on checking an existing decision rather than buying a fresh one.

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?

Explicitly instructs to call this whenever someone hands you a decision_id you are about to rely on. It also names the alternative (resolving fresh) and explains why this is cheaper, providing both when-to-use and when-not-to-use context.

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