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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is known. The description adds genuine context beyond that — it triggers a 24-hour commit-reveal subprotocol — but says nothing about what rejection destroys, funds at risk, reversibility, or what the caller must do next.

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?

Two short sentences, zero filler, with the actor and action front-loaded and the subprotocol consequence second. It is arguably over-compressed rather than padded, but nothing is wasted.

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 destructive, non-reversible-looking state transition with no output schema and two undocumented required params, the definition is thin: it never explains the consequences of the 24h window, what the buyer must later submit, or what the tool returns.

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 coverage is only 33%: commitHash is documented in the schema (keccak256(observedDeliverable || salt)), and the description adds nothing to it beyond the name. agentId and intentId are entirely undocumented in both places, leaving the buyer/agent role and intent binding to inference.

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?

A specific verb and resource: the buyer 'rejects the deliverable' using a commit hash, scoped to round 1. It is distinguishable from siblings like agentpact.reveal or agentpact.open_dispute, though the 'Class B' qualifier is unexplained jargon and no sibling it is distinct from is named.

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 '(round 1)' parenthetical implies a phase in a multi-round flow, which hints at timing, but there is no explicit statement of when to use this versus open_dispute, reveal, or submit_reveal_preimage, and no prerequisites or exclusions.

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