all_coinsReturn the full CoinDesk Data (formerly CryptoCompare) coin list with symbol, name, CoinId, algorithm, proof type, and asset type for every tracked cryptocurrency.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| Data | No | Coin data keyed by symbol | |
| BaseLinkUrl | No | Base URL for coin links | |
| BaseImageUrl | No | Base URL for coin images |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {}
+]Output schema / (root)Previous value: -nullNew value: +{
+ "description": "Complete cryptocurrency list",
+ "properties": {
+ "BaseImageUrl": {
+ "description": "Base URL for coin images",
+ "type": "string"
+ },
+ "BaseLinkUrl": {
+ "description": "Base URL for coin links",
+ "type": "string"
+ },
+ "Data": {
+ "additionalProperties": {
+ "type": "object"
+ },
+ "description": "Coin data keyed by symbol",
+ "type": "object"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations clearly indicate readOnly, idempotent, and non-destructive behavior. The description's 'Return' aligns with these hints, and there is no contradiction. The tool appears to have no side effects.
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 a single concise sentence that lists the output fields without unnecessary detail. It is well-structured and easy to parse.
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?
The description is sufficient for a simple list retrieval, but it does not mention potential limitations such as pagination, response size, or sorting. These are not critical, but a bit more context would make it complete.
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 there is nothing to explain. The schema coverage is complete (no parameters). The description does not need to add parameter semantics.
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 that the tool returns the full list of tracked cryptocurrencies from CoinDesk Data, specifying the exact fields included. This is unambiguous and distinguishes it from other tools like top_market_cap or price.
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?
No explicit guidance is provided on when to use this tool versus alternatives such as top coins or price queries. The description is self-explanatory for a simple listing, but it does not mention use cases or exclusions.
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.
Several tool families overlap heavily: ask_pipeworx, its beta, and grounded variants, the six polymarket_* tools, and the three price endpoints (price, price_full, price_multi) can be confused despite distinct purposes. Long descriptions provide some disambiguation, but an agent must read carefully to select the correct tool.
Tool names mostly follow snake_case with verb_noun or noun_noun patterns (all_coins, compare_entities, top_market_cap), and related families share clear prefixes (histo_*, polymarket_*). Minor deviations exist (bare verbs like remember/forget, brand names like ask_pipeworx), but the overall pattern is readable and consistent.
With 46 tools, the server is far beyond the 3-15 well-scoped range and nearly double the 25-tool threshold for 'too many'. Many tools are unrelated to the server's apparent crypto purpose (generate_llms_txt, scan_dependency, memory helpers), making it feel like a general-purpose utility rather than a focused data service.
The crypto data surface is fairly complete (spot, historical, top lists, news, social stats, exchange metadata), and the Pipeworx meta-tools (ask_pipeworx, deep_research, entity_profile) cover a broad range of factual queries. However, there are notable gaps: no direct way to fetch pipeworx:// citation URIs, and no advanced crypto order-book/trade endpoints, leaving some workflows as dead ends.