Skip to main content
Glama

get_hold_state

Read-onlyIdempotent

Is the trend behind a position I own still intact? For a position already owned: whether the trend behind it is intact, weakening or broken. Exits come before entries. THE SELL-SIDE READ: is the case for a name you already hold still intact, or deteriorating? Returns published trend state, the hold label, maturity-late flag, overnight gap-risk level, the book's regime, and watch_flags: which deterioration conditions are TRUE in the published read (structure light off green, hold read in its lowest band, leadership lost, mature leg, trend cold, high gap risk, earnings within 7 trading days), plus the mechanical rules those states flip on. BTC-USD / ETH-USD return the crypto IN|CASH daily-close state. Up to 3 comma-separated symbols. Reports conditions only; impersonal, it never reads your entry, size or account. Free sample: up to 3 symbols per call, headline fields, from the morning 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>"
    },
    "name": "get_hold_state"
  }
}

Input Schema

NameRequiredDescriptionDefault
symbolYesTicker, e.g. NVDA — or up to 3 comma-separated (NVDA,AMD,BTC-USD)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / symbol / description
      Previous value: -"Ticker, e.g. NVDA — or up to 10 comma-separated (NVDA,AMD,BTC-USD)"New value: +"Ticker, e.g. NVDA — or up to 3 comma-separated (NVDA,AMD,BTC-USD)"
  2. Added

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already cover read-only and idempotent, but the description adds substantial context beyond them: the full list of returned fields, the meaning of each watch_flag (structure light off green, hold read in its lowest band, leadership lost, mature leg, trend cold, high gap risk, earnings within 7 trading days), the mechanical rules those states flip on, and the special crypto behavior for BTC-USD/ETH-USD. It also discloses a free-tier limit of 3 symbols per call with headline fields only, which an agent needs before choosing batch size.

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 core facts are front-loaded, but the same idea is stated three times: the opening question 'Is the trend behind a position I own still intact?', then 'whether the trend behind it is intact, weakening or broken', then 'THE SELL-SIDE READ: is the case ... still intact, or deteriorating?'. The watch_flags parenthetical is dense but earns its space; the duplicated framing does not.

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, the description carries the full burden of explaining return values, and it does so field by field, including the flag semantics and crypto special case. For a one-parameter read tool whose safety profile is already in annotations, nothing an agent needs in order to call it correctly is missing.

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

Parameters4/5

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

The single parameter is fully documented in the schema (ticker, up to 3 comma-separated), so the baseline is a 3. The description still adds meaning the schema does not carry: the crypto symbols return a distinct IN|CASH daily-close state, and the free sample caps at 3 symbols per call, which affects how the agent should batch.

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 description states a specific read verb and resource: for a position already held, it returns whether the trend is intact, weakening, or broken, and enumerates the fields returned (hold label, maturity-late flag, gap-risk level, regime, watch_flags). It positions itself against the entry-side tools via 'Exits come before entries' and 'THE SELL-SIDE READ', so an agent can tell it apart from get_buy_list. It never distinguishes itself from the near-identical get_hold_state_live sibling, which keeps it off a 5.

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

Usage Guidelines4/5

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

'For a position already owned' plus 'Exits come before entries' gives a clear condition for reaching for this tool rather than an entry scanner. 'Reports conditions only; impersonal, it never reads your entry, size or account' further scopes what questions it can answer. There is no explicit exclusion or routing guidance for the live variant, so the alternative-selection story is incomplete.

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