Skip to main content
Glama

Market structure

get_structure

Chart structure of one symbol, read live and in English, one answer per call. Charts per market: crypto spot 1M, 1W, 1D, 4H, 1H; futures (USDⓈ-M perpetual) and tokenized stocks 1D, 4H, 1H, 15m, 5m. Per chart: trend, the support and resistance zones above and below the price (near and far, each with its distance and tests), the one zone the price is inside (shown once, as inside), the nearest support and resistance, RSI, EMA200, breaks (confirmed with the date of the closing candle, pending, live with the role the level had before), the last closed candle's time, whether the current candle is closed or still forming, and volume against its 20-bar average. Also the live price, the nearest and major close triggers across charts, and when the data was read (asOf). Freshness: status is ok, or stale (the live ticker was unavailable or older than 30 s, so the last close is the price), partial (some chart could not be read; missing says which and why), or stale_partial. A symbol with no readable chart returns the reason and costs nothing. market spot (default) or futures; a futures symbol keeps the quote it names (BTCUSDC is the USDC perpetual); spot is USDT only; only symbols the app lists are readable, so a perpetual with no spot listing is not available. user_price is the user's own number (an entry, a cost, a target), never a level: the answer gives its distance from the live price and its place against each chart's zones. Costs 2 credits for a read that carries at least one chart, and is billed, not a free read.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "symbol": "<symbol>",
      "market": "<market>"
    },
    "name": "get_structure"
  }
}

Input Schema

NameRequiredDescriptionDefault
marketYesspot
symbolYes
user_priceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond the sparse annotations (readOnlyHint=false, openWorldHint=true) by disclosing cost (2 credits, billed, not a free read), the freshness state machine (ok / stale with the 30 s threshold / partial with missing reasons / stale_partial), and that an unreadable symbol costs nothing. That is strong behavioral context; the annotation readOnlyHint=false is consistent with a billed read rather than a contradiction. Minor gap: 'openWorldHint=true' implies an external live market dependency that is only loosely reinforced by the 30 s staleness rule, and pagination/response envelope behavior is not addressed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and the answer contents are front-loaded, and nearly every clause carries real information (chart intervals per market, freshness states, billing). But it is delivered as one dense run-on paragraph with stacked parentheticals and semicolon chains, which makes the freshness and cost rules hard to locate on a fast read; bulleting or splitting into 'returns / freshness / parameters / cost' would cost nothing and gain a lot.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and a complex, high-cardinality response, the description effectively serves as the output contract — enumerating each per-chart field, the inside/near/far zone distinctions, break states, and asOf. Combined with the availability constraints and failure modes, an agent has enough to call it correctly and interpret what comes back without further documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry the load and it does: market is spot (default) or futures with the rule that a futures symbol keeps the quote it names (BTCUSDC = USDC perpetual) and spot is USDT only, while user_price is explicitly 'the user's own number (an entry, a cost, a target), never a level' and yields its distance from live price and its place against each chart's zones. This adds semantics the bare schema (an enum, a string, a positive number) could never convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb and resource: 'Chart structure of one symbol, read live and in English, one answer per call,' and the body enumerates exactly what the answer contains (trend, zones, RSI, EMA200, breaks, volume vs 20-bar average, asOf). The scope is unmistakable, but it never positions itself against siblings such as market_context or get_price, so an agent must infer which one to pick.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: it explains 'market spot (default) or futures', that only app-listed symbols are readable, and that a perpetual with no spot listing is unavailable — useful preconditions for calling it. However, there is no explicit when-to-use or when-not-to-use guidance versus alternative tools, and no statement of which situations warrant a 2-credit call instead of a cheaper read.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources