Skip to main content
Glama

rank_tokens

Two-stage token ranking: run the cheap screen, then concurrently fetch deterministic chart evidence only for the strongest candidates. Quick charts 5 candidates over month+3months; standard charts 10 over day+month+3months+year; deep charts 20 and requires explicit opt-in. Returns evidence for user review and never creates a proposal.

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": {
      "chains": "<chains>"
    },
    "name": "rank_tokens"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo
sortsNoDefaults to gainers_30d + volume_1d. Optional supplements: gainers_1d, gainers_90d, gainers_365d, market_cap.
chainsYes
periodsNo
deepOptInNoRequired when mode=deep
verifiedOnlyNoDefault true
candidateLimitNoOverride merged candidate cap, max 100
minVolume1dUsdNoDefault 50000
minMarketCapUsdNoDefault 5000000
includeUnverifiedNoDefault false
chartCandidateLimitNoOverride chart cap, max 20

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does a good job: it discloses the two-stage pipeline, that chart fetches run concurrently and only for the strongest candidates, and that deep mode requires explicit opt-in — a real safety/cost gate an agent must know about. The final clause clarifies it is read-only with respect to proposals. It does not disclose cost, latency, rate limits, or what 'verified' filtering means.

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

Conciseness4/5

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

Front-loaded with the core mechanism, then the mode tiers, then the safety-relevant caveat — a sensible order. The semicolon-separated mode list is dense but information-bearing; almost no filler remains, though it could be broken into shorter sentences for scanability.

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

Completeness4/5

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

For an 11-parameter tool with no output schema, the definition covers the mode semantics, the default/override relationship, the deep-mode gate, and what the caller gets back (evidence for review, not a proposal). Remaining gaps are minor: the meaning of verifiedOnly and how chain identifiers are supplied are left entirely to the schema.

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?

Schema coverage is 73%, and the description covers the biggest gap: the 'mode' enum has no schema description, yet the description specifies exactly what each mode does in terms of candidate count and periods, which effectively governs candidateLimit, chartCandidateLimit, and periods defaults. That meaning is not derivable from the schema alone. It does not explain the 'chains' or 'sorts' inputs at all.

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?

States a specific verb and resource ("Two-stage token ranking") and explains the actual mechanism: cheap screen first, then concurrent chart-evidence fetch for the top candidates. It distinguishes itself from the propose_* family by stating it "never creates a proposal," but it never names the adjacent siblings screen_tokens, discover_tokens, or get_token_chart, so the boundary with those is left to inference.

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?

The mode tiers (quick=5 candidates, standard=10, deep=20 with explicit opt-in) give implicit guidance on choosing a depth, and the deep opt-in acts as a usage gate. However, there is no explicit statement of when to use this instead of screen_tokens or discover_tokens, nor any prerequisite or exclusion conditions.

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