Initiate a purchase of a service. Creates a fund hold for the agreed price. Call ae_get_service first to obtain service_id and verify pricing.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | Input data as a JSON string. Must conform to the service's input_schema. | |
| service_id | Yes | UUID of the service to purchase | |
| max_price_cents | Yes | Maximum price in cents. Must be >= service base price. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the 'fund hold' side effect, which is a significant behavioral trait. However, it does not explain what happens on failure, reversibility, or how the hold is resolved, leaving gaps in transparency.
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 sentences, front-loaded with the main purpose and followed by a useful prerequisite. Every sentence earns its place with no redundancy.
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?
The tool is a mutation with no output schema, so the description should explain the outcome. It mentions the fund hold but does not describe the return value or how to track the transaction. The existence of ae_get_transaction helps, but the description itself is incomplete for a financial operation.
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 100%, and the description adds workflow context by linking service_id to obtaining it via ae_get_service and max_price_cents to the agreed price. This adds value beyond the schema but does not provide deep semantic details beyond what is already documented.
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's action ('Initiate a purchase of a service') and the key behavior ('Creates a fund hold for the agreed price'). It distinguishes from sibling tools by emphasizing purchase initiation and referencing ae_get_service for pricing, which sets it apart from read-only or negotiation tools.
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 provides explicit usage guidance by instructing the agent to call ae_get_service first to obtain service_id and verify pricing. This is a clear precondition, though it does not mention when to avoid this tool or use alternatives like ae_negotiate.
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.
Each tool targets a distinct resource and action, from service discovery and registration to transaction negotiation and output verification. The only overlapping pair, ae_discover_services and ae_list_services, is explicitly differentiated by semantic search vs. categorical browsing.
All tools follow the consistent ae_verb_noun pattern in snake_case, with verbs like create, get, list, deliver, and verify. The uniform prefix and naming convention make the API predictable and easy to navigate.
With 13 tools, the server is well-scoped for a marketplace platform, covering service lifecycle, transaction workflow, wallet, trust, and agent management. Each tool serves a distinct purpose and none feel redundant, keeping the surface area manageable.
The tool set covers the full service and transaction lifecycle: register/list/discover/get services, create/negotiate/deliver/verify transactions, plus wallet and trust queries. Minor gaps exist such as no service update/delete or transaction listing, but core workflows are fully supported.