price_historyPrice series for one destination: measured span, stats, a downsampled sample of points and any regime breaks. Historical observations only, never a live quote or a recommendation.
| Name | Required | Description | Default |
|---|---|---|---|
| rail | No | optional: restrict to one rail | |
| destination | Yes | destination slug, as returned by list_destinations |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The read-only annotation is reinforced and supplemented by the description: it is historical observations only, never a live quote or recommendation. The mention of a downsampled sample and regime breaks gives useful behavioral context beyond the annotation.
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, front-loaded sentence states the core purpose before providing clarifying constraints. Every clause adds value, with no filler or repetition of schema details.
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?
Although there is no output schema, the description names the key output categories (span, stats, downsampled sample, regime breaks) and the main exclusions (live quote, recommendation). It could go further on empty-history edge cases or formatting, but it provides enough for an agent to call the tool confidently.
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 input schema already provides 100% description coverage for both parameters, including the destination slug format and rail enum. The tool description adds little parameter-specific detail beyond confirming the destination scope, so the baseline of 3 is appropriate.
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 names the exact resource (price series for one destination) and enumerates the returned components: span, stats, downsampled sample, and regime breaks. It also differentiates from siblings by explicitly stating it is historical only and never a live quote or recommendation.
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 clearly establishes when to use the tool: when historical price data for a destination is needed. It also provides a when-not signal by ruling out live quotes and recommendations, though it does not explicitly name sibling tools like current_vs_history as alternatives.
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.
list_destinations is clearly a discovery tool, while price_history provides the full series and current_vs_history provides a comparative summary. There is some overlap because both single-destination tools report stats, but the stated outputs are distinct enough for an agent to choose correctly.
list_destinations follows a verb_noun pattern, but price_history and current_vs_history are noun phrases with no consistent verb. The names are readable and reasonably descriptive, but the mix of conventions prevents a higher score.
Three tools is on the small side, but each covers a meaningful slice of the price-history workflow: enumerate available series, inspect a series, and get a current-vs-history summary. It is slightly sparse but not unreasonably so for a focused read-only server.
The server covers discovery and per-destination historical detail, plus the headline comparison statistic, so core read-only use cases are supported. Obvious gaps such as raw full-resolution series, cross-destination comparison, or any write/live-quote operations are absent but appear to be out of scope.