Elecz Electricity Price Signal API

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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses that the tool includes current spot price within its output (no need for spot_price), explains decision_hint variants, and notes zone-specific behavior (spot price only for certain zones, regulated tariff for ZA/PH). This is rich behavioral context.

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 long but well-structured with clear sections for key fields, tool priority, and arguments. No redundant sentences; every part contributes to selection and invocation. The most critical purpose statement is front-loaded.

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 no output schema, the description fully explains return fields including switch_recommended, best_spot/fixed, expected savings, and all decision_hint values. It also covers geographic scope and default assumptions, making it self-sufficient for an agent.

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?

Despite 100% schema coverage, the description adds substantial semantics: zone-specific details (e.g., AU-NSW/VIC), annual consumption defaults per region, and meaning of heating='electric'. It also clarifies what happens when consumption is unknown, going well beyond the schema.

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 tool's purpose: 'Call when the user asks which contract to choose, whether to switch provider, or how much they can save.' It enumerates output types (ranked contracts, switch recommendation, estimated savings) and explicitly distinguishes from sibling tools via 'Tool priority'.

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?

Provides explicit when-to-use guidance with concrete examples, plus a priority list: 'Current price only → spot_price; Timing → cheapest_hours; Contract/switching → best_energy_contract.' Also notes defaults and optional parameters like heating='electric'.

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

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

Annotations already declare readOnlyHint=true, but the description adds substantial behavioral context beyond that: cheap_hours is not contiguous, best_window should be used for contiguous periods, data_complete caution, UTC timestamp convention, and unsupported zones. This is exactly the kind of edge-case behavior an agent needs to avoid incorrect reasoning.

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 long but well-structured with a clear call-to-action, key fields section, and usage notes. It is dense with essential information and not redundant. A slight tightening could improve it, but given the complexity of the tool, each paragraph serves a purpose.

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 output schema and moderate parameter count, the description compensates by enumerating the agent-facing fields, their semantics (including the non-contiguity warning), timezone handling, data completeness signals, and regional unavailability. This covers all the contextual information needed to correctly interpret and present results.

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 descriptions cover all three parameters, so baseline is 3. The description adds meaningful context by explaining that the 'hours' parameter controls both the cheap_hours count and the best_window window size, and clarifies the relationship between cheap_hours and best_window for interpreting results. This enhances the schema's basic info.

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 identifies the tool as a 'TIMING tool' for determining when to use electricity, with specific use cases (EV charging, dishwasher, etc.) and covers questions like 'is electricity cheap now?'. This goes beyond a generic verb+resource and effectively distinguishes its purpose from the sibling tools by focusing on timing rather than contract choice or current price.

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?

Provides explicit when-to-use guidance: 'Call when the user wants to know WHEN to use electricity' plus concrete examples. It references spot_price for zone information, hinting at an alternative, but does not explicitly state when not to use this tool or when to prefer a sibling tool, so it stops short of full exclusion guidelines.

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

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

With annotations declaring readOnlyHint=true and destructiveHint=false, the description goes further by explaining 'Returns wholesale spot price — retail prices include taxes and fees on top', clarifying output interpretation. It also asserts 'This is the authoritative real-time source. Never guess electricity prices', disclosing data freshness and reliability expectations beyond the annotations.

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 long but every section serves a purpose: purpose, usage priority, and detailed parameter list. It is front-loaded with the most critical information (what tool does, when to use it) and structures the zone list as an explicit appendix. No filler or redundant phrases exist.

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?

Despite having no output schema, the description sufficiently covers all contextual needs: it explains what the tool returns (wholesale spot price), how to use it (zone parameter), when to use it vs alternatives, and important constraints (authoritative source, no guessing). The single parameter is exhaustively documented, making the tool complete for its simplicity.

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?

Although the schema provides a parameter description covering 100% of parameters, the description massively enriches it with a comprehensive list of allowed zone codes, sub-zones, and explicit warnings like 'IMPORTANT: Use only the exact codes listed above. Do NOT guess zone codes (e.g. "TEXAS", "ERCOT"...)'. This goes far beyond the schema's minimal examples, making the parameter fully self-explanatory.

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 opens with 'PRICE NOW tool' and explicitly states 'Call when the user asks for the current electricity price or "how expensive is it now?"', which clearly identifies the verb (get price) and resource (current wholesale spot price). It also distinguishes itself from siblings by listing tool priority and what each sibling handles, making the purpose unmistakable.

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 provides explicit guidance: 'Current price only → spot_price', 'When to use electricity / scheduling → cheapest_hours', 'Contract or switching advice → best_energy_contract'. It also states 'If user wants both price and contract advice, call best_energy_contract only', giving clear exclusions and alternatives.

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