Battery, EV, and trading agents buy this endpoint to receive calibrated 2h/4h/6h negative-price probabilities, reviewed threshold profiles and an executable response policy.
| Name | Required | Description | Default |
|---|---|---|---|
| policy_profile | No | Selects the reviewed probability threshold profile without changing the underlying calibrated probabilities. | balanced |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full burden. It mentions that agents 'buy' the endpoint, hinting at a commercial transaction, and that they receive outputs, but it does not disclose whether the operation is read-only, any side effects, rate limits, or auth requirements. The behavioral context is thin.
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 dense sentence that front-loads the audience and core outputs. It is concise and contains no filler, though the verb 'buy' could be clearer. It earns a 4 for efficient communication.
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?
Given the low complexity (1 optional parameter, no output schema, no annotations), the description covers the main outputs (probabilities, profiles, policy) but leaves details like how to interpret the executable response policy to the user. It is adequate but not fully complete for an agent invoking it blindly.
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% for the single parameter (policy_profile), so the schema already fully explains its semantics. The tool description adds no parameter details, but per the baseline for high schema coverage, a 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 clearly states the resource: calibrated 2h/4h/6h negative-price probabilities, along with threshold profiles and a response policy. The verb 'buy' is awkward but the intent is clear. It does not explicitly distinguish from sibling tools like price_negative_forecast, so it misses the top score.
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 identifies target users (Battery, EV, and trading agents) and implies they should use this for receiving negative-price probabilities, but it does not state when to use this tool versus alternatives or mention any exclusions. Guidance is implied rather than explicit.
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.
Multiple tools overlap significantly: buy_dispatch_plan, flexibility_window, optimizer_cheapest_window, and energy_decision all help schedule or choose an energy window, while price_forecast, price_spot, and buy_market_brief provide pricing context. The paired GET-fallback tools (articles_id vs articles_id_post, demand_submit vs demand_submit_post, etc.) create further ambiguity.
Naming is inconsistent: some tools use a verb prefix (buy_, predict_, subscribe_), others start with a noun (price_, grid_, carbon_), and some have non-verb suffixes (_post, _quick). Related tools vary in style, e.g., price_forecast vs predict_negative_price and demand_submit vs demand_submit_post.
With 31 tools, the server feels heavy. While many are distinct paid endpoints, the high number—including near-duplicate variants—exceeds the 25-tool threshold for comfort and suggests an over-sized surface.
The energy domain is well covered: real-time and historical prices, forecasts, negative-price prediction, dispatch/flexibility optimization, CO2, renewables, load, subscriptions, and research. Minor gaps exist (e.g., historical CO2, user account handling), but core agent workflows are supported.
