parse_user_agentParse a User-Agent string into browser, OS, device type (mobile/tablet/desktop/bot) and a bot flag (keyless, offline, heuristic).
| Name | Required | Description | Default |
|---|---|---|---|
| user_agent | Yes | The User-Agent string. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and no destructive actions. The description adds that it extracts specific categories (browser, OS, device type, bot flag), which provides some behavioral context beyond annotations, but it does not disclose edge cases or error handling.
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?
Single sentence, front-loaded with action verb, lists output categories without extraneous words. Every part of the description is necessary and informative.
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?
With no output schema, the description lists structural output components (browser, OS, device type, bot flag), which provides a good sense of return values. It could be more precise about the format, but for a simple parsing tool it is sufficiently complete.
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% with the single 'user_agent' parameter clearly described. The description does not add new meaning beyond the schema, so baseline score of 3 is appropriate.
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 begins with 'Parse a User-Agent string,' clearly specifying the verb and resource. It lists exact output fields (browser, OS, device type, bot flag) and distinguishes itself from sibling tools, none of which parse user agents.
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 implies use for extracting structured data from user-agent strings but gives no explicit guidance on when or when not to use it, nor mentions alternative tools. It is adequate but lacks decision-making context.
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.
ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all perform overlapping routed-search functions; ask_pipeworx_beta is even documented as currently identical to ask_pipeworx. The three Polymarket discovery tools (polymarket_edges, polymarket_arbitrage, polymarket_fill_risk) also have blurry boundaries around finding vs. validating vs. executing on edges.
Nearly all tools use snake_case with a verb_noun or descriptive pattern (ask_pipeworx, validate_claim, resolve_entity, list_subscriptions). Minor deviations exist — bare verbs like remember/recall/forget and noun_first names like bet_research or entity_profile — but the convention is largely predictable and readable.
32 tools is heavy, and the set spans unrelated domains: Pipeworx data routing, prediction-market trading, agent memory, subscription management, npm dependency checks, user-agent parsing, and llms.txt generation. The sub-clusters each earn their place individually, but as a single server surface the count is unjustifiably large and scattershot.
The Pipeworx research surface is quite complete (lookup, grounded answers, deep research, entity profiles, comparisons, validation, entity resolution, discovery, feedback), and memory/subscription lifecycles are fully covered. However, the server has no coherent single domain — user-agent parsing (the server's namesake) has only one tool, while unrelated utilities like generate_llms_txt and scan_dependency appear with no supporting ecosystem.