Skip to main content
Glama

cryptoport-port

by com.thecryptoport

Dated catalysts, windowed

catalysts
Read-only

FREE. Dated, falsifiable events named on the board, optionally limited to those due within N days. Past-due events are excluded when a window is given. Upstream briefs land on about 71% of days; board content is same-day roughly half the time and is never more than three days old. Not real-time. Every payload carries stale / stale_days / built_from_brief_date — read them. Commentary on public statements, not advice. This tool does not accept portfolio, position or risk-profile inputs and will refuse them with HTTP 400.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
windowNoLook-ahead window in days; omit for all catalysts
paymentNoOptional x402 payment payload (the value you would put in the X-PAYMENT header, base64). Call without it first: the tool answers with the machine-readable 402 terms, you settle testnet USDC on Base Sepolia, then call again with this field.

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already mark readOnlyHint, but the description adds substantial behavior beyond that: data staleness distribution, non-real-time nature, stale_* payload fields, refusal of unsupported inputs with HTTP 400, and a disclaimer about commentary. This far exceeds what annotations provide.

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

Conciseness5/5

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

The description is dense but every sentence earns its place: scope, freshness behavior, payload caveats, refusal behavior, and payment flow. Critical constraints are front-loaded before operational details.

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 a tool with no output schema, the description does well by naming the key payload fields (stale / stale_days / built_from_brief_date) and covering payment, freshness, and refusal behavior. It could go further by describing the general event shape, but nothing essential for invoking the tool 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful semantic detail for the window parameter (past-due exclusion behavior) and for payment (full call-without-it then settle-then-retry sequence), pushing it above the baseline.

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 identifies the resource as dated, falsifiable events on the board and explains that catalysts can be windowed by due date. It is specific but does not explicitly compare against siblings like latest_board or search, so it slightly misses on direct differentiation.

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?

Provides clear operational guidance: how the window filters past-due events, that the data is not real-time, and the two-step x402 payment flow. It lacks explicit 'use this instead of X' statements, but the staleness and freshness context strongly implies when it is appropriate.

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

All cryptoport-port toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation4/5

Each tool has a distinct target: current board, historical snapshot, single coin detail, events, search, and stance history. The main overlap risk is between latest_board and board_snapshot, and between coin and stance_history, but descriptions clearly differentiate current vs. historical and record vs. arc.

Naming Consistency3/5

Names are readable and mostly noun-phrase style (board_snapshot, latest_board, stance_history), but the set mixes single nouns (coin, catalysts) with a verb (search) and uses inconsistent snake_case across only some names. The pattern is not chaotic, but lacks a uniform convention.

Tool Count5/5

Six tools is well-scoped for a read-only board querying service: one for the full board, one for search, one for details, one for history, one for events, and one for historical snapshots. The count feels right for the domain.

Completeness4/5

The core read workflows are covered: get the current board, inspect a single coin, search, see the stance history, and list catalysts. The only notable gap is that board_snapshot is not yet functional, so true historical board snapshots are unavailable; however, stance_history partially fills the historical need.

Resources