Emergency stop, one call: suspends the account, revokes every API key, session, delegation and venue credential, and returns all unwind calldata for the owner. Auth required.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | optional reason, recorded |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key actions (suspend, revoke, return calldata) and the auth requirement. Lacks explicit mention of irreversibility or side effects, but the description is reasonably transparent given no annotations.
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?
Concise single sentence with clear, structured listing of effects. No redundant information.
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?
Completely describes the tool's purpose and required auth. The return value 'unwind calldata' is mentioned but not elaborated; this is acceptable without an output schema, though a bit more detail could improve completeness.
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?
The optional 'reason' parameter is fully described in the schema (100% coverage), so baseline is 3. The description does not add extra meaning beyond the schema.
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?
Clearly describes the tool's action: suspends the account, revokes all credentials, and returns unwind calldata. Distinct from siblings as an emergency stop.
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?
Labels it as an 'Emergency stop, one call' which implies usage in critical situations, and notes 'Auth required'. However, it does not explicitly state when not to use it or mention alternatives.
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. Within the prediction market domain, prepare vs create vs submit are clearly differentiated by signing model (client-signed vs server-signed). Even similar-sounding tools like check_spend and check_pm_order are unambiguously scoped to general spending vs PM orders, and their descriptions reinforce the boundary.
All 47 tools follow a consistent verb_noun pattern with lowercase snake_case. Verbs like get, list, create, cancel, revoke, prepare, submit, set, remove, and poll are used uniformly. There is no mixing of styles or vague verbs like 'process' or 'run', making the surface highly predictable.
47 tools is significantly above the 25-tool threshold for 'too many'. While the server covers a broad and complex domain (prediction markets, policy, delegations), the sheer count makes the surface heavy and potentially overwhelming. Some consolidation (e.g., merging related PM order operations) could reduce cognitive load without sacrificing functionality.
The tool set provides comprehensive lifecycle coverage across all major subdomains: authentication, policy versioning, delegation CRUD (prepare/confirm/list/get/revoke/renew), intent management, PM order flow (create/cancel/list/prepare/submit/check), credential management (store/list/revoke), balance and top-up operations, and account-level actions (export, offboard, panic). Minor omissions exist (e.g., no dedicated tool to view a single credential in detail or update an intent), but agents can work around these with existing tools.