arrivalsReal-time predicted arrivals at a stop. Pass the naptanId from stop_search (e.g. "940GZZLUOXC"). Results are sorted by timeToStation (seconds away), nearest first.
| Name | Required | Description | Default |
|---|---|---|---|
| naptanId | Yes | Stop NaPTAN id, obtained from stop_search. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds context: 'real-time', 'predicted arrivals', 'sorted by timeToStation (seconds away)'. No contradictions.
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, front-loaded with purpose. No extraneous words. 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?
Single-parameter read-only tool with strong annotations. Description sufficiently covers purpose, input source, and result sorting. No output schema needed.
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 100% and already describes naptanId as obtained from stop_search. Description adds an example value but does not fundamentally expand meaning beyond schema. Meets baseline with minor enhancement.
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?
Description clearly states 'Real-time predicted arrivals at a stop.' with specific verb 'arrivals' and resource 'stop'. It distinguishes from siblings like stop_search (which returns stops) and plan_journey (journey planning).
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?
Explicitly instructs to pass the naptanId from stop_search, providing a prerequisite. Mentions sorting order but no exclusion conditions or alternative tools. Adequate for a simple read tool.
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.
Many tools have distinct purposes, but there are multiple ask_pipeworx variants and several Polymarket tools with similar functions, causing potential confusion. Most other tools are clearly differentiated, but the overlap in query and betting tools reduces clarity.
Naming conventions are inconsistent: some tools use snake_case (ai_visibility_check), others use descriptive phrases (ask_pipeworx, generate_llms_txt), and some are very short (arrivals). Lengths vary widely, and there is no uniform pattern.
37 tools is excessive for a coherent server; the scope is too broad, spanning transport, data lookups, prediction markets, and utilities. This suggests a lack of focus, making the server feel like a bundled collection rather than a well-scoped toolkit.
The server covers multiple domains but lacks depth. London transport tools are partial (e.g., no real-time tube positions), and domains like weather or stock quotes rely on the ask_pipeworx meta-tool rather than dedicated tools. The surface is broad but not comprehensively complete in any area.