Creates a new ERC-721 SLA agreement NFT. Requires x402 payment ($0.01). Returns payment instructions.
| Name | Required | Description | Default |
|---|---|---|---|
| duration | Yes | Duration in years (5, 7, or 10) | |
| bondAmount | Yes | Bond amount in iUSDC base units | |
| counterparty | Yes | Counterparty wallet address | |
| coverageLevel | No | Insurance coverage level (0-3) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the burden. It discloses a payment requirement ('Requires x402 payment ($0.01)') and that it returns payment instructions, but the relationship between creating the NFT and the payment is ambiguous—whether minting is immediate, deferred, or contingent on the payment is unclear.
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 description is two concise sentences, front-loaded with the primary action, and every word adds value. No wasted 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?
With no output schema and no annotations, the description's 'Returns payment instructions' is vague—does not specify format, content, or next steps. The payment flow (pay first vs. receive instructions first, when NFT is actually minted) is incomplete, and for a tool with 4 parameters and a payment/mint process, this is insufficient.
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 parameters are well documented in the schema. The description adds no specific parameter meaning beyond the schema, though it does mention the payment context which relates to the transaction but not to any individual parameter.
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 clearly states the tool 'Creates a new ERC-721 SLA agreement NFT,' combining a specific verb ('creates'), resource ('SLA agreement NFT'), and scope ('new'), which distinguishes it from siblings like 'renew_sla' or 'check_agent_insurance'.
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 description implies use for creating new SLAs by saying 'new,' but does not explicitly contrast with alternatives like renew_sla or early_exit. It mentions a payment requirement but no when-to-use or when-not-to-use guidance beyond that.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools have similar purposes, such as the three simulation tools (simulate_action, simulate_paid_action, simulate_paid_action_batch) and the two payment wrappers (pay_then_call, insurelink_charge). While descriptions clarify distinctions, an agent may struggle to choose correctly without careful reading.
All tool names use lowercase snake_case with a consistent verb_noun or verb_noun_noun pattern (e.g., get_reputation, subscribe_attestation_freshness). No mixing of conventions or styles.
With 28 tools, the surface is larger than typical. While each tool serves a specific function, many could be consolidated (e.g., simulation tools, payment wrappers) to reduce cognitive load. The count exceeds the 25-tool threshold for 'too many'.
Core operations for reputation, attestation, SLA lifecycle, and payments are present. However, gaps exist: no tool to list individual SLAs or update an SLA beyond renewal/reset, and no dispute or pricing query tool. The set covers the domain but has notable missing operations.