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

Far beyond the annotations, it discloses cost (0.10 USDC x402 on Base, 10 free signed-wallet calls per rolling 30 days), the required X-Wever-Wallet-Proof bound to the exact JSON arguments and path, the 25.00 USDC order-value cap, and the concrete effect of disputing (release freeze plus retained expiry refund to the hirer). Security posture (no private keys, no payee/payer substitution, no granted authority) and the out-of-scope arbitration UI are also spelled out.

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 essential effect and blocking semantics are front-loaded, but the paragraph then packs in deposition rail facts, a full enumeration of normal states, and operator-process caveats that read as reference documentation rather than invocation guidance. Several clauses ('adapter grants no authority', 'live funded acceptance remains a manual operator step') are boilerplate that dilute the actionable content.

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, paid, proof-authenticated mutation with no output schema, the description supplies the critical context: cost, auth binding, caps, state effects, refund path, and where to find schemas. What is missing is the expected response and whether retries with the same idempotency_key are deduplicated, which matters given a required idempotency key alongside idempotentHint=false.

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 25% — only evidence_reference carries a description — so the description needed to compensate and mostly does not: order_id, proof_hash and idempotency_key receive no explanation of format or role. It does add the useful pointer to /api/workorder-contract for evidence bounds and notes that the wallet proof is bound to the exact JSON arguments, but a caller still cannot tell what proof_hash must commit to or how idempotency_key is honored.

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 gives a specific verb and effect: pause release of the order and record bounded evidence in the proof inbox, and the endpoint POST is named. However, it does not distinguish this tool from close siblings such as wever_dispute-open, wever_dispute-submit-evidence or wever_purchase-dispute, so overlap with those must be inferred rather than read.

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?

Who may invoke it ('either authenticated party') and what it blocks are stated, and the state machine implies eligibility (funded/accepted/delivered orders). But there is no explicit 'use this instead of X when Y' guidance versus the dispute-open/submit-evidence siblings, nor a statement of preconditions such as which order states permit a dispute.

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