Compute the per-update basis between a perpetual contract’s mark price and its index price for one symbol; infer crypto or equity from the symbol when asset class is omitted.
Derivative price against its index price, per update, from one symbol.
| Name | Required | Description | Default |
|---|---|---|---|
| end_ns | Yes | ||
| symbol | Yes | ||
| start_ns | Yes | ||
| asset_class | No | Which market answers. Inferred from the symbol's source when omitted. |
Changes observed during successful MCP inspections.
v0.3.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full disclosure burden. 'per update' hints at tick-level, high-cardinality output, which is useful, but nothing is said about read-only nature, data availability, symbol-class behavior, or result volume — the equity-vs-crypto computation split lives only in the schema text, not the 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?
A single, tightly packed sentence with zero filler and the core metric front-loaded. It is a noun fragment rather than a complete statement, but nothing is padded or redundant.
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?
For a four-parameter time-series tool with no annotations, no output schema, and only 25% schema coverage, the one-line description is far too thin. An agent cannot learn the timestamp units, the meaning of the asset_class inference, or the output shape from what is provided.
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 only 25% (only asset_class is annotated). The description's 'from one symbol' usefully clarifies that symbol takes a single value rather than a list, but start_ns and end_ns are left entirely unexplained in both schema and description, including that they are nanosecond epochs.
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 phrase 'derivative price against its index price' identifies the metric (perp mark vs index basis) and 'from one symbol' pins the input shape, so the resource is recognizable. However there is no verb (compute/return) and no differentiation from close siblings like 'basis' or 'spot-future-basis', which an agent must disambiguate by name alone.
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?
The description gives no when-to-use guidance, no exclusions, and never names an alternative. With 'basis' and 'spot-future-basis' in the sibling list, the agent gets no signal about which of the three basis tools to pick.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.