FindEnergyRates Electricity Rates

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the bar is lower; the description still adds real scope information by disclosing the at-least-one-parameter constraint and the 'current rate only / no historical' limitation. It does not describe response shape or multi-match behavior when utility is partial.

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?

Three sentences, each earning its place: definition first, input constraint second, scope limitation third. No filler and nothing buried.

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, the description does some work by saying only the current rate is returned, and it covers the input requirement. It leaves open what comes back if utility matches multiple entries or if both state and utility are supplied, which is a modest gap for a lookup tool.

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 100%, so baseline is 3, but the description adds meaning beyond the schema: the schema lists no required parameters (required: 0), while the description correctly states at least one of state/utility must be supplied. That is genuine additive semantics, though the partial-match behavior of utility is already covered by 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?

States a specific resource — the current utility price-to-compare (PTC) / default-service rate — and even defines what the benchmark means, so an agent knows exactly what it retrieves. It does not differentiate itself from siblings get_utility_by_zip or search_plans, which keeps it short of a 5.

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?

Explicitly states the input requirement ('supply state, utility, or both; at least one is required') and an exclusion ('historical PTC is not available... must not be inferred'). It stops short of naming the alternative sibling tools to use instead, so it is clear context without explicit routing.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuinely non-obvious behavior: a ZIP can map to multiple TDSPs, all matches are returned, and the agent must surface all rather than pick one — a result-cardinality trait not derivable from 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?

Two sentences, zero filler, and the core resolution behavior is front-loaded before the multi-match caveat. Every clause earns its place.

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, the description carries return-value burden, and it does explain that the electric utility (and Texas TDSP) matches are returned. It does not specify any other fields in the response, but for a single-parameter resolver this is nearly complete.

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% with one parameter, so the schema already documents the 5-digit format and example. The description's mention of '5-digit US ZIP' restates rather than extends the schema, so baseline 3 applies.

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?

Names a specific verb (resolve) and resource (ZIP code → electric utility/TDSP) with clear scope, including the Texas-specific TDSP concept. The purpose is unmistakably distinct from siblings get_ptc_rates and search_plans, which deal with rates and plan search rather than geographic utility resolution.

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 use case (have a ZIP, need the serving utility) is implied clearly, but the description never states when to reach for this versus the sibling tools or any prerequisite ordering. The multi-match instruction is behavioral guidance for handling results, not tool-selection guidance.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond that: results are limited to the last 7 days, the `status` field can mean `no_data_for_scope` rather than no plans, pricing is anchored to EFL-disclosed usage (500/1000/2000 kWh) and not recalculated for exact usage, and unpriced plans are returned last. This is rich, non-obvious behavior that an agent needs to interpret results correctly.

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 dense but well-organized: scope and ordering are front-loaded, then the 7-day window and status caveat, then the optional `usage_kwh` behavior. Every sentence adds information, and the most important constraints (required params, no bulk export) come first. It is longer than the typical description, but the length is justified by the genuinely complex pricing-anchor behavior that would otherwise be a trap for an agent.

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?

For a read-only search tool with 100% schema coverage and no output schema, the description covers everything an agent needs to call it correctly: required scope, result ordering, recency limit, status-field interpretation, and the full semantics of the optional pricing parameter. The sibling tools are different enough (get_ptc_rates, get_utility_by_zip) that no additional differentiation is needed. The only thing not described is the exact output shape, but the absence of an output schema and the detailed field list in the description make that acceptable.

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%, so the schema already documents all 7 parameters. The description adds value by explaining the semantics of `usage_kwh` in depth: how the anchor is chosen (nearest of 500/1000/2000, ties to 1000), what fields are added, what `anchor_shape` means, and that `est_monthly_cost_dollars` is always null. It also clarifies the `utility` parameter's exact-match requirement and the error-based discovery trick. The only minor gap is that it doesn't restate every parameter, but the schema already covers them.

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 states a specific verb ('Search'), a precise resource ('live residential electricity plans'), and a clear scope ('for one utility in one state, ordered cheapest first'). It explicitly distinguishes itself from bulk/unscoped export and names the required scope, so an agent can tell it apart from siblings like get_ptc_rates or get_utility_by_zip without opening the schema.

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 explicitly says both `state` and `utility` are required, warns that the API does not support bulk or unscoped export, and explains when to pass `usage_kwh`. It also gives a concrete fallback for an uncertain utility value ('call with a wrong value once — the error lists every utility we hold for that state'). This is clear when-to-use guidance with an alternative strategy.

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