list_feedsList the curated law & courts feeds (id, title, category, source). Optionally filter by category (government, law) or keyword. Pass an id to read_feed.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Keyword to match in feed title/source/description. | |
| category | No | Filter by category: government, law. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate the tool is read-only, open-world, idempotent, and non-destructive. The description adds the filtering behavior and the fields returned, which is consistent but not highly detailed. 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: first describes the action and result, second describes the optional parameters and sibling pointer. 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?
For a simple list tool with no output schema, the description covers the essential behavior: listing feeds with optional filtering. It could mention the default behavior when no filter is applied, but that's a minor omission.
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 descriptions for both parameters. The description mentions 'filter by category (government, law) or keyword' which matches the schema. It adds the fact that feeds are 'curated law & courts' but doesn't provide deeper semantics 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?
The description clearly states the action (List), the resource (curated law & courts feeds), and the returned fields (id, title, category, source). It also distinguishes from the sibling tool 'read_feed' by instructing users to pass an id to that tool.
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 specifies optional filters by category or keyword, and directs users to read_feed for individual feed retrieval. This provides clear context for when to use this tool versus its sibling.
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.
Multiple tool families overlap heavily: ask_pipeworx/ask_pipeworx_beta/ask_pipeworx_grounded all route through the same 5,721 tools, polymarket_edges/polymarket_arbitrage/bet_research/polymarket_fill_risk all target prediction-market opportunities, and ai_visibility_check vs scan_competitor_ai_presence cover the same probe. An agent would struggle to pick the right one without reading every description carefully.
There are coherent subfamilies (ask_pipeworx_*, polymarket_*, remember/recall/forget, list/read/fetch_feed), but the overall set mixes verb-first names (list_feeds, validate_claim, fetch_feed) with noun-first names (entity_profile, bet_research, deep_research) and adjective-led names (recent_alerts, recent_changes). The inconsistency is noticeable but not chaotic.
34 tools is heavy for a server branded 'Law Feeds,' and many tools are off-domain (Polymarket betting, npm dependency scanning, AI visibility marketing, generic memory). The breadth could justify a larger catalog, but the overlapping research/Polymarket tools inflate the count beyond what the surface needs.
As a general data-gateway, the set is fairly complete: routing, grounded answers, deep research, entity resolution, comparison, subscriptions, memory, and feedback are all covered. Relative to the 'Law Feeds' identity, though, the surface is shallow — only list_feeds, read_feed, and fetch_feed serve that purpose, with no feed search, management, or update capabilities.