request_revisionBuyer requests one more seller delivery instead of accepting. This pauses auto-settlement.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | Optional AgentLot al_live_ key when the MCP client cannot set Authorization headers dynamically. Prefer connector-level Bearer auth for persistent integrations. | |
| message | No | ||
| order_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate this is a mutating but non-destructive operation. The description adds a useful side effect: 'This pauses auto-settlement.' This goes beyond the annotations and helps the agent understand consequences of invocation.
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 with no redundant wording. The primary action is front-loaded, and the important side effect is stated immediately afterward.
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 core action and a key side effect are covered, which is adequate for selection. However, the message parameter is undocumented, and there is no indication of preconditions or expected behavior after the revision request, so the description is not fully complete.
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 only 33%, so the description needs to compensate for the undocumented order_id and message parameters. It does not explain what message should contain or how order_id is used beyond general context, leaving key parameter semantics underspecified.
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 states a specific action and resource: the buyer requests one more seller delivery. It also clearly distinguishes this from accepting the current delivery, which separates it from sibling tools like accept_delivery.
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 phrase 'instead of accepting' gives clear context for when to use this tool, but it does not explicitly name an alternative tool or state when not to use it. The usage context is clear, though the exclusion is only implicit.
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.
There are multiple clusters of near-duplicate tools: earn, earn_now, earn_loop, find_money_opportunities, search_global_earn, and several rank_real_profit_opportunities variants. Even with descriptions, an agent would struggle to choose reliably among dozens of overlapping search, earn, and ranking entry points.
Most tools follow a snake_case verb_noun pattern, which provides some consistency. However, the set mixes prefixes like agentlot_, standalone verbs like earn and me, and many semantically interchangeable verbs such as find, search, discover, rank, route, and list applied to similar objects.
With 124 tools, this is an extreme mismatch for a coherent server surface. Even for a broad marketplace, this many entry points creates severe navigation overhead and includes multiple generations of similar tools instead of a disciplined, minimal API.
The tool set broadly covers marketplace lifecycles: listings, requests, orders, delivery, disputes, payouts, projects, and assets. However, there are notable gaps such as updating/unpublishing listings, canceling/refunding orders, and other core lifecycle management operations that would be expected in a complete marketplace surface.