list_loopsList all available Jawz loops. Returns loop metadata, access status, and which loop is currently active for this user. Every published loop is free and open. Deprecated loops you are entitled to are included with deprecated: true.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| loops | No | ||
| terms_glossary | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and destructiveHint, so the safety profile is covered. The description adds valuable behavioral detail beyond that: every published loop is free and open, and deprecated loops are included only if entitled, with a deprecated: true flag. This helps an agent understand access semantics and response shape.
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?
The description is two sentences with no filler: the main action is front-loaded, and additional behavioral details are packed into the second sentence. Every clause adds information an agent would need.
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?
The tool is a simple zero-parameter listing operation with an output schema available, so the description does not need to explain return values in depth. It covers the key contextual points: scope (all available), user-specificity (active/entitled), access model (free/open), and deprecated-loop handling. Nothing essential is missing.
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 tool has zero parameters and the schema is empty, so there is nothing for the description to clarify. The description correctly focuses on return content instead. With no parameters, this is a strong baseline outcome.
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 opens with a specific verb+resource pair, 'List all available Jawz loops,' which clearly distinguishes it from the sibling get_loop and run_loop tools. It also specifies what is returned: loop metadata, access status, and the currently active loop. This leaves no ambiguity about the tool's purpose.
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 clearly frames the tool as the enumeration entry point for all loops, including the nuanced cases of free/open loops and deprecated entitled loops. It does not explicitly name alternatives or provide when-not-to-use guidance, but the list-versus-get/run distinction is strongly implied by the phrasing and sibling names.
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 target clearly distinct resources—regime, liquidity, conditions, prices, ETF profiles, data health—and the three history tools are explicitly separated as price, flow, and judgment. The main ambiguity is get_chapter vs run_chapter, which both return chapter framework content and differ only in usage logging, though the descriptions call this out explicitly.
The set follows a consistent snake_case verb_noun pattern: get_ for reads, list_ for enumeration, run_ for framework text, and score_ for position drift. The only wrinkle is run_chapter/get_chapter, where 'run' doesn't mean execution but rather 'return framework text and log usage,' making the verb semantics slightly less predictable.
22 tools is on the heavy side but the set is organized into recognizable clusters: macro regime, liquidity/conditions, histories, portfolio drift, ETF/prices, loops/framework, and data health. Each tool appears to earn its place, so the count is slightly high but not bloated.
The surface is comprehensive for a read-and-analyze macro/portfolio server: current reads, historical timeseries, data freshness, event calendar, ETF look-through, drift scoring, and loop navigation are all covered. Minor gaps exist—no direct portfolio/position listing tool and non-US central-bank event dates are intentionally not tracked—but these are acknowledged and workable.