Net capital flow across the canonical L1 bridge over the last 24h, valuation-clocked: every included flow carries an explicit price observation, and legacy unpriced rows are excluded with valuationCoverageComplete saying so. A window with no priced flows returns netUsd null with a dataNote rather than fabricated zeros. The one read no L2-only view can produce.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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?
With no annotations provided, the description carries the full burden of behavioral disclosure. It goes beyond a simple read statement by explaining valuation methodology ('valuation-clocked'), exclusion of unpriced rows with a flag, and the null-with-dataNote behavior instead of fabricated zeros. This is exemplary transparency for a read tool with no annotations.
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 and front-loaded with the core purpose. However, the second sentence is dense and contains somewhat cryptic phrasing ('valuation-clocked', 'The one read no L2-only view can produce') that might reduce clarity. It is appropriately sized but could be streamlined for readability.
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?
Given no output schema and no annotations, the description adequately explains return behavior for the tool's complexity. It mentions key output fields (netUsd, valuationCoverageComplete, dataNote) and handles edge cases. For a zero-parameter, read-only tool, this is complete and will guide an agent effectively.
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, so per the rubric baseline is 4. The schema is empty and additionalProperties is false, so there are no parameter semantics to explain. The description correctly omits parameter details, as none exist, and does not need to compensate.
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 a specific verb+resource: 'Net capital flow across the canonical L1 bridge over the last 24h'. It distinguishes from sibling tools by focusing on bridge flows specifically and adds a unique qualifier ('The one read no L2-only view can produce'). This is a precise, non-tautological statement.
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?
It provides clear context for when to use (to get bridge flow data) and hints at uniqueness, but it does not explicitly exclude alternatives or name specific sibling tools. The phrase 'The one read no L2-only view can produce' gives some differentiation but is not a direct usage guideline. No explicit when-not or alternative names are given.
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.
Every tool targets a distinct slice of Robinhood Chain intelligence: token data, premiums, perp markets, stablecoin flows, corporate actions, risk checks, and sentiment. Even overlapping areas (e.g., get_token vs. search_tokens, get_stock_premiums vs. get_stock_multipliers) are clearly separated by purpose. No two tools appear to duplicate each other's core function.
The tool names mix conventions: most are verb-led (get_, search_, check_), but several are noun phrases (chain_composition, perps_markets, stablecoin_flows). Within the get_ group the pattern is consistent, but across the full set the mixing of prefixes and bare nouns makes the naming less predictable. Still, each name is descriptive enough to infer its role at a glance.
With 26 tools, the set exceeds the 25-tool threshold for 'too many'. While the domain is broad (covering tokens, perps, stablecoins, corporate actions, flows, and narratives), the sheer number risks over engineering and agent confusion. Some tools could be grouped (e.g., perps_funding and perps_markets might be one, get_token and get_token_candles might share). The scope feels stretched.
The surface covers a comprehensive array of Robinhood Chain data: token details, market premiums, perp funding, stablecoin flows, settlement graphs, corporate actions, and risk assessment. Minor gaps exist (e.g., no direct wallet transaction history, no governance queries), but for the stated purpose of 'chain intelligence' the coverage is robust and includes both live and historical reads.
