unsubscribeCancel a subscription by id. Ownership is enforced — you can only cancel your own subscriptions. The row is deactivated (not deleted) so its historical events stay available via recent_alerts.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Subscription id (uuid) returned by subscribe. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds beyond annotations: explains that the row is deactivated (not deleted) and ownership is enforced. Annotations only indicate non-destructive and idempotent; description fills in behavioral details.
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. First sentence conveys action and constraint; second explains the effect. Every sentence earns its place.
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?
For a one-parameter tool without an output schema, the description covers action, constraints, and side effects. Could mention return value or error handling, but not essential.
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 100% with a clear description for the 'id' parameter. The tool description adds no additional semantic detail beyond what the schema already provides.
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 verb 'Cancel a subscription by id' and specifies the resource (subscription). It distinguishes from siblings like 'subscribe' and 'list_subscriptions' by detailing ownership enforcement and deactivation behavior.
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 clear context for when to use (own subscriptions) and explains constraints (ownership enforcement, deactivation). Does not explicitly mention alternative tools, but the purpose is self-contained enough for an agent.
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 have clearly distinct purposes, but there is some overlap among ask_pipeworx, ask_pipeworx_grounded, and deep_research, as well as between discover_tools and suggest_questions. However, detailed descriptions help differentiate them.
Naming conventions are highly inconsistent, mixing snake_case (ask_pipeworx, forget), camelCase (discoverTools, suggestQuestions), and underscores (ai_visibility_check, compare_entities). No predictable pattern.
33 tools is on the high side, but the broad domain (finance, pharma, prediction markets, etc.) partly justifies it. However, some tools like forget, remember, recall seem generic and could be separated.
The tool surface covers a wide range of functionalities: visibility checks, pipeworx queries, entity profiles, comparisons, subscriptions, memory, and more. Minor gaps may exist in real-time data or specific niche sources.