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

Annotations already flag destructive/idempotent/open-world, and the description adds substantial non-obvious context: domain-bound operator signature, durable nonces for concurrent retries, a 100.00 USDC per-UTC-day resolution cap, 14-day expiry with automatic timeout refund to the payer, fee separation from principal, and pending external custody/audit. Nothing contradicts the annotations.

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 information, but it is a dense run-on mixing prerequisites, pricing, caps, expiry policy, audit status and a doc pointer with no visual separation. The core purpose is not front-loaded — the first sentence leads with a signing requirement rather than what the call resolves.

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, 9-param mutation with no output schema and low schema coverage, the description covers settlement behavior, caps, expiry refunds, auth headers and pricing, and redirects to /api/dispute-contract for schemas and recovery limits. The main remaining gap is a description of what a successful resolution 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 11% (just reason_uri), yet the description supplies meaning for several key params: operator_authorization ('domain-bound operator signature for the exact dispute and outcome'), idempotency_key (via 'durable transfer nonces'), the atomic amount pair ('explicit atomic amounts summing to the locked total'), and the action enum. dispute_id and reason_sha256 remain undocumented beyond a pointer to /api/dispute-contract, which slightly limits the score.

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 names a specific verb and resource ('resolve dispute') and enumerates the three resolution outcomes (release to payee, refund to payer, split) plus a secondary extend action, so the agent knows exactly what the call does. It does not, however, distinguish itself from siblings like wever_dispute-open, wever_dispute-status or wever_dispute-submit-evidence, leaving the boundary implicit.

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?

It states which outcomes exist and describes the extension mode, but never says under what conditions an operator should choose release vs refund vs split, nor when to call dispute-status instead. Usage is implied by the outcome names rather than explained.

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