Skip to main content
Glama

Electricity and gas

energy
Destructive

Compare offers (compare, from_bill), unit_prices, history, suppliers, appliance (running cost) and fixation alerts (watch, watch_status, watch_confirm, watch_cancel). Indicative, not verified.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "energy"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoSupplier id, e.g. cez-prodej
mwhNoYearly MWh
kindNofridge, washer or heating (appliance)
rateNoTariff rate, e.g. D02d
emailNoE-mail for the alert (watch)
limitNoMax rows
tokenNoToken from a link or e-mail
actionYesOperation to run; help {topic:"energy"} lists each one's arguments
detailNocompact (default) or full
localeNoLanguage, e.g. cs
nt_mwhNoYearly low-tariff MWh
offsetNoRows to skip
vt_mwhNoMWh billed (from_bill)
countryNoCountry code, e.g. CZ
commodityNoelectricity or gas
distributorNoDistributor id, e.g. cez-distribuce
fixation_endNoLast day of the fixed price, YYYY-MM-DD (watch)
current_monthlyNoCurrent monthly cost

Output Schema

NameRequiredDescriptionDefault
moreNoHow to fetch the next page
limitNo
totalNoAll matches, not just this page
offsetNo
returnedNo
cross_border_noteNo
commission_disclosureNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / action / description
      Added value: +"Operation to run; help {topic:\"energy\"} lists each one's arguments"
    • addedInput schema / properties / detail
      Added value: +{
      +  "description": "compact (default) or full",
      +  "enum": [
      +    "compact",
      +    "full"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / fixation_end / description
      Previous value: -"Fixation end date (watch)"New value: +"Last day of the fixed price, YYYY-MM-DD (watch)"
    • changedInput schema / properties / id / description
      Previous value: -"Supplier id"New value: +"Supplier id, e.g. cez-prodej"
    • addedInput schema / properties / offset
      Added value: +{
      +  "description": "Rows to skip",
      +  "type": "number"
      +}
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": {},
      +  "properties": {
      +    "commission_disclosure": {
      +      "type": "string"
      +    },
      +    "cross_border_note": {
      +      "type": "string"
      +    },
      +    "limit": {
      +      "type": "number"
      +    },
      +    "more": {
      +      "description": "How to fetch the next page",
      +      "type": "string"
      +    },
      +    "offset": {
      +      "type": "number"
      +    },
      +    "returned": {
      +      "type": "number"
      +    },
      +    "total": {
      +      "description": "All matches, not just this page",
      +      "type": "number"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

C2.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare destructiveHint=true and readOnlyHint=false, so the safety burden is partly carried already. The description adds real value with the caveat 'Indicative, not verified', warning that results are estimates, but it never says which of the ten actions mutate state, what the alert flow confirmation does, or what watch_cancel destroys. For a multi-action tool where only some operations are writes, that omission matters.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with the action inventory front-loaded and the reliability caveat closed out. Nothing is padded, though the parenthetical enumeration reads as a terse code list rather than explanatory prose, which costs some readability without wasting space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Ten actions and eighteen parameters — with an output schema present — demand more than a name list. The description never indicates which parameters pair with which action (mwh/vt_mwh/nt_mwh for compare vs. from_bill, fixation_end/email/token for the watch flow), leaving the agent dependent on the schema's pointer to help. For a tool of this complexity it is under-specified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every one of the eighteen parameters is already documented in the schema, which sets the baseline at 3. The description adds only a light mapping of parameter context to actions (from_bill, watch, appliance) and no format or constraint detail beyond what the schema states. It neither compensates for nor detracts from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates the ten actions (compare, from_bill, unit_prices, history, suppliers, appliance, watch, watch_status, watch_confirm, watch_cancel) and gives a partial gloss for two of them ('Compare offers', 'appliance (running cost)'). However, half the list is bare operation names with no verb or resource described, so an agent cannot tell what unit_prices, history, or watch_status actually do from the text alone. It is an index rather than a purpose statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no routing to alternatives. Siblings like price_watch and comparisons plausibly overlap with the watch and compare actions, but the description never distinguishes them or says which tool to prefer. The only structural hint — that help {topic:"energy"} lists each action's arguments — lives in the schema, not the description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources