List delivery candlesticks.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | End timestamp in seconds | |
| from | No | Start timestamp in seconds | |
| limit | No | Maximum number of data points to return | |
| settle | No | Settlement currency for delivery (e.g. usdt, btc) | |
| contract | Yes | Delivery contract identifier (e.g. BTC_USDT; may use mark_/index_ prefix for price type) | |
| interval | No | Time interval for data points |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint true, and destructiveHint false, covering the safety profile. However, the description adds no behavioral context beyond these annotations, such as return format, pagination, or rate limits, which would be useful given the minimal description.
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, front-loaded and without unnecessary words. However, it is arguably too terse, lacking any elaboration that would improve agent comprehension, though it is not under-specified to the point of being useless.
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 tool has 6 parameters, no output schema, and many related sibling tools. The description is too minimal to fully contextualize the tool's role, especially without mention of return values or how it compares to other candlestick tools, making it insufficient for an agent to understand the full scope.
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?
Schema description coverage is 100%, with all six parameters having clear descriptions. The description itself adds no parameter-level detail, so the baseline of 3 applies; the schema carries the burden.
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 'List delivery candlesticks' clearly states the action (list) and resource (delivery candlesticks), identifying the specific market type. It distinguishes from sibling candlestick tools by specifying delivery contracts, though it could be more explicit about the scope and prefix conventions.
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 guidance is provided on when to use this tool versus other candlestick tools like cex_fx_get_fx_candlesticks or cex_options_list_options_candlesticks. The description lacks context on typical use cases, exclusions, or alternative tools.
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.
Every tool is clearly scoped by its domain prefix (spot, fx, options, etc.) and resource type, with no two tools serving the same purpose. Even similar data types like candlesticks and order books are unambiguously separated by market.
The naming follows a strong pattern: cex_<domain>_<verb>_<resource>. However, the use of 'get' vs 'list' is occasionally inconsistent (e.g., cex_fx_get_fx_tickers vs cex_spot_list_currencies), and some names are verbose with version suffixes like 'v4'.
With 63 tools, this is an extreme count that will overwhelm an agent. While the breadth covers many product lines, the vast number of endpoints makes selection difficult and violates the typical scope for an MCP server.
The tool surface comprehensively covers public market data across spot, futures, options, delivery, earn, margin, lending, launch, and social products. Minor gaps exist (e.g., no historical trade depth, no single-ticker convenience methods), but the core data needs are fully addressed.