Time series (latest vintage per date) for up to 8 series codes. Each point is [date, value, shortid]; the shortid is the signed-passport handle for get_datum.
| Name | Required | Description | Default |
|---|---|---|---|
| codes | Yes | ||
| limit | No | most recent N points per series, default 24, max 400 |
Changes observed during successful MCP inspections.
Input schema / properties / limit / descriptionPrevious value: -"most recent N points per series, default 24, max 120"New value: +"most recent N points per series, default 24, max 400"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose real behavioral traits: vintage selection ('latest vintage per date'), point tuple ordering [date, value, shortid], and the batch cap. It omits the outer return container (map keyed by code vs. list of series), ordering, and behavior for unknown codes.
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?
Two dense sentences with no filler, and the core scope is front-loaded. The missing verb makes the opening slightly telegraphic, but nothing is wasted.
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?
With no annotations and no output schema, the description must cover behavior and returns. It gives the per-point shape but not the overall response structure, ordering across series, or missing-data handling — gaps an agent will hit on the first call.
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 coverage is 50%: `limit` is documented in-schema, while `codes` has only a bare array type. The description compensates by naming what `codes` are (series codes) and restating the 8-item cap, which is the meaningful semantic for that parameter.
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 resource and scope are concrete: time series for up to 8 series codes, latest vintage per date. The verb is elided (it reads as a noun phrase), but an agent can still tell this is a multi-series fetch. It does not explicitly contrast with get_series or get_bulk, so sibling differentiation is only partial (via the get_datum hand-off note).
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?
Usage is implied by the batch constraint ('up to 8 series codes') and by the follow-up hint that shortid feeds get_datum. There is no explicit statement of when to choose this over get_series or get_bulk, nor any exclusion or precondition.
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.