Cancel your open or partially filled CC/USDC order. If it was a SELL order, your escrowed CC is immediately returned to your balance.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | Yes | ||
| agent_id | Yes | ||
| order_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that escrowed CC is returned for sell orders, a useful behavioral trait. However, no annotations exist, so description carries full burden; it lacks details on error handling or security (e.g., role of API key).
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?
Two sentences, no filler. Front-loaded with action and resource, then adds condition for sell orders. Every sentence adds value.
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?
Adequate for a simple cancel operation given no output schema, but missing error scenarios, response format, and prerequisites (e.g., order ownership). Could be improved with minimal extra context.
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 0% and description does not explain any parameters beyond implying order_id. API key and agent_id are completely undescribed, leaving the agent without guidance on what values to provide.
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?
Clear verb 'cancel' and specific resource 'open or partially filled CC/USDC order'. Distinct from sibling tools like place_cc_order and fill_cc_order.
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?
Provides context for when to cancel (open or partially filled) but no explicit when-not or alternatives. Implies usage but no guidance on choosing this tool over others.
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.
Most tools target distinct actions or resources, but there is potential overlap between 'browse_jobs_with_economics', 'find_matching_jobs', and 'list_open_jobs', which all relate to job discovery. Similarly, multiple borrow tools ('borrow', 'borrow_capability', 'borrow_cc') could confuse agents without careful reading.
Tool names consistently use snake_case with verb_noun pattern. Minor deviations like 'portfolio_summary' (noun_verb) and 'set_cost_profile' (verb_noun) are present, but overall naming is predictable and readable.
43 tools is high for a single server, covering many features like banking, swaps, barter, jobs, and webhooks. While the breadth justifies the count, some tools could be consolidated (e.g., multiple borrow tools) to reduce cognitive load.
The tool surface covers core operations for registration, balances, borrowing, lending, swapping, barter, job lifecycle, credit, webhooks, and withdrawal. Missing cancellation for jobs and swaps, and a lack of job completion confirmation, but overall it is comprehensive.