Top-5 front-running signals (policy event + trade spike 30d prior). Updated weekly Mon 07:00 UTC. Returns signal_id, policy_date, hs_code, spike_multiple, confidence. FREE (lead magnet, public — signals delayed 7 days from detection).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max signals to return (default: 5, max: 50) | |
| since | No | Filter signals on/after date, YYYYMMDD |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full transparency burden. It discloses the update schedule, public access, and delayed signals, and enumerates the returned fields, which is solid behavioral disclosure. It doesn't mention rate limits or explicitly say it's read-only, but the operation is clearly a query.
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?
Three dense sentences, each contributing new information: what the signals are, when they refresh, and what payload/access conditions to expect. No filler or redundancy.
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 or annotations, the description still covers key returned fields, access conditions, and freshness, which an agent needs for decision-making. It doesn't clarify sorting when limit > 5 or field interpretation, but those are minor for selecting and invoking the tool.
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%, so the schema already fully documents limit and since parameters. The description adds no parameter-level semantics beyond implying default top-5 selection; baseline 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 identifies tool as providing top-5 front-running signals and explains the signal criteria (policy event + trade spike 30 days prior). It clearly states the resource and context but does not explicitly differentiate from sibling tools like wave_portfolio or wave_signal.
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?
States update cadence (weekly Mon 07:00 UTC) and public/free access with a 7-day delay, giving an agent clear context on data freshness and availability. No explicit 'use instead of X' guidance or exclusion conditions, but the context is enough to infer when to call.
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 signal tools (front_run_watch, prediction_signals, wave_signal) serve similar purposes and could be confused, though each has a distinct data source. Similarly, soul_insights and soul_stack_feed both present agent-generated content, creating some ambiguity.
All names use snake_case, but there's no consistent pattern: some are verb-first (get_prices, search_products), some are brand-prefixed nouns (soul_bounties, wave_portfolio), and mixed usage like daloopa_query and soul_verify. The inconsistency is readable but not predictable.
16 tools for a multi-source market data server is reasonable; there are no outright redundant tools, though a few (think, fusion_capabilities) feel auxiliary. The count is slightly above ideal but well within acceptable bounds.
The server provides extensive read-only browsing (soul_bounties, soul_insights) but lacks corresponding action tools like claiming a bounty or purchasing insights, creating dead ends. For a 'market', there are no execute/trade/buy operations, leaving significant gaps for agent workflows.