verify_riskRuns paid AegisAI risk verification and never runs verification for free. An x402-aware MCP client can pay and retry this tool automatically; unpaid calls return the canonical payment challenge.
| Name | Required | Description | Default |
|---|---|---|---|
| plan | No | Product plan. Evidence is advertised but not yet available. | basic |
| content | Yes | Text to assess before an external action. | |
| context | No | ||
| sources | No | ||
| requestedChecks | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey read-only and non-destructive behavior. The description adds meaningful behavioral details: the tool is never free, unpaid calls return a canonical payment challenge, and an x402-aware client can pay and retry. This goes beyond the structured annotations without contradicting them.
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 concise sentences with the key paid-verification constraint front-loaded. The term 'x402-aware' is unexplained jargon, but the text overall is efficient and free of unnecessary 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?
Despite having 5 parameters, nested objects, enums, and no output schema, the description omits important context: what risk verification actually checks, what the result looks like, and how the parameter combinations affect behavior. The payment challenge is covered, but the tool's operational semantics are incomplete for an agent deciding how to invoke it.
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 40%, and the description adds no information about parameters, plan options, context object, sources, or requested checks. The description does not compensate for the low coverage, leaving several parameters semantically under-explained.
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 ('Runs paid AegisAI risk verification') and resource, which distinguishes it from the sibling monitor tools. It could be more precise about what 'risk verification' evaluates, but it is not a tautology and identifies the tool's core function.
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 gives payment and retry context but does not explain when to use verify_risk versus alternatives. It does not mention any conditions, prerequisites, or exclusions, leaving the agent to infer the use case from the name and parameters.
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 pairs a single verb with a distinct resource or action, and descriptions explicitly separate state-changing, state-free, verification, and list/get operations. Even similar tools like the two challenge creators are clearly differentiated by challenge type (DNS TXT vs endpoint), so misselection is unlikely.
All tools follow a consistent verb_noun pattern using clear verbs like create, get, list, register, stop, update, and verify. The monitor_ prefix is used uniformly for monitor-related resources, while distinct domains such as risk and capabilities have their own readable nouns.
At 17 tools, the set is slightly heavier than the typical well-scoped range, but each tool covers a distinct operation across subscriptions, endpoints, alerts, policy evaluation, and risk verification. The count is reasonable given the breadth of the platform.
Core read and write operations exist for subscriptions, endpoints, and alerts, but lifecycle coverage has notable gaps: there is no endpoint get/update/delete, no subscription activation/resume, and no way to enable delivery after verification. Several workflows end at stopped or pending states unless external actions occur.