Who Represents This Address

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

With no annotations available, the description carries the full burden and it delivers: disclosing the AI operator, the free-tier rate limit of '50 lookups per day per IP address' and the Pro API-key alternative, plus precise edge-case behavior for local.mayor (only ~280 cities, exact Census match, 'otherwise null'). These are highly actionable behavioral constraints an agent needs before invoking.

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 dense: rate limits, exact-match semantics, inclusion/exclusion scope, and null behaviors each earn their place. It is slightly weakened by front-loading the vendor/AI disclosure ('Operated by an AI...') ahead of the core purpose and by running several distinct facts into one long paragraph.

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?

Complexity is moderate, but with no output schema the description must explain what the JSON contains, and it does so in granular detail: federal, state, and local districts, officeholders, state_executives, local boundaries, and the mayor null case. It lacks only error/geocoding-failure behavior and explicit routing to the batch sibling, which keeps it from a full 5.

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% and the schema already documents address as free-text including city, state and ZIP with a concrete example and maxLength. The description only repeats 'free-text U.S. Street address' and adds no new parameter syntax, format, or constraints beyond the schema, so the 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?

The description states a specific verb-resource pairing: 'returns its 119th Congress district, state legislative districts (upper and lower) and current officeholders...' for a single United States free-text street address. The singular 'a' street address distinguishes it from the find_representatives_batch sibling, and the scope of outputs is enumerated exhaustively.

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 gives clear usage context: the tool is for a single U.S. street address, geocoded to Congress/state/local districts and officeholders. It adds a usable exclusion, listing what will NOT be returned ('No city council, county or school-board officials'), which is an effective when-not-to-use signal. It does not explicitly name find_representatives_batch as the alternative for multiple addresses.

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 no annotations, the description fully carries the behavioral burden. It discloses the operator, per-address lookup counting, free tier limits and refusal behavior, Pro quota behavior, the single-message JSON-RPC requirement, and the approximate return structure including per-address results/errors, count, and usage.

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 and information-rich, covering operator disclosure, batch usage, result shape, and quota rules in three sentences. The operator disclosure is somewhat auxiliary for tool selection, but overall there is no wasted repetition.

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 that there is no output schema and no annotations, the description appropriately covers invocation format, auth/quota modes, top-level return shape, and per-address error behavior. It does not enumerate every field in a lookup result, but the provided structure is sufficient for an agent to call the tool correctly.

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 schema already fully describes the single 'addresses' parameter with item constraints, min/max items, and a description. The tool description adds batch-level context and quota semantics, but it does not need to explain the parameter further, 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 opens with 'Same as find_representatives for a list of 1 to 40 U.S. street addresses in one call,' clearly identifying the operation, resource, and batch scope. It also differentiates this tool from the sibling find_representatives by emphasizing the list/one-call behavior and not being inside a JSON-RPC array.

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 frames the tool as the batch counterpart to find_representatives and gives specific invocation constraints such as sending it as a single JSON-RPC message. It does not explicitly state a decision rule like 'use find_representatives for a single address,' but the context strongly implies the appropriate use case.

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