openstates-mcp-server

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

Annotations already declare readOnly, openWorld, and idempotent hints, so the description doesn't need to restate safety. It adds useful behavioral context by explaining that `include=votes` returns full vote tallies and per-legislator positions, and that `include=actions` returns complete history. It also clarifies the two distinct identifier input methods.

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 four sentences long, front-loaded with the core purpose, and every sentence conveys distinct information: purpose, identifier alternatives, include behavior, and preference. No redundancy or filler.

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?

The description covers the main usage paths and include options. It does not explicitly state that at least one identifier must be supplied, and the schema lists 0 required parameters, which could be ambiguous. However, the phrasing 'Accepts either...' strongly implies a required choice. With a full schema and an output schema present, the description is otherwise 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?

While schema descriptions cover each parameter individually (100% coverage), the description adds critical grouping semantics: it explains that `jurisdiction`, `session`, and `bill_id` form a three-part path alternative to a single `openstates_id`. This relationship is not evident from the schema alone and meaningfully guides parameter selection.

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 a specific verb+resource: 'Fetch full detail for a specific state bill.' It clearly distinguishes from sibling tools that fetch other entity types (committees, events, jurisdictions). The alternate identifier formats are also described.

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 advises using `include` to get related data in one call 'rather than searching again' and explicitly recommends preferring `openstates_id` to avoid session lookup. It implies the tool is for when you already have a bill identifier, but it doesn't explicitly say 'use only when you have an ID; otherwise search first.'

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, openWorldHint, and idempotentHint, which cover the safety profile. The description adds value by disclosing that the tool is 'Experimental,' that data is not available for all states, and that the return includes name, classification, and membership roster conditionally. This goes 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 extremely concise, consisting of three clear sentences: purpose, conditional return, and workflow/caveat. Every sentence earns its place, with no fluff or repetition of schema details.

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 tool's simplicity (get by ID), the presence of a detailed output schema, rich parameter descriptions, and annotations covering safety, the description is complete. It adds the crucial experimental caveat and directs users to the correct source for the ID, making it well-rounded 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?

The input schema already provides 100% coverage with detailed descriptions for both parameters, including the meaning of 'memberships,' 'links,' and 'sources.' The description restates the memberships behavior but adds no new parameter semantics beyond what the schema provides, 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 uses a specific verb ('Fetch') and resource ('committee detail') with an explicit identifier ('OCD organization ID'), clearly distinguishing this from sibling search tools. It also names the source tool (openstates_search_committees) for obtaining the ID, reinforcing its unique role.

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 a clear workflow by stating 'Obtain the committee_id from openstates_search_committees,' implying this tool is used after a search. It also warns that 'not all states have committee data,' offering context for when the tool may not work. However, it does not explicitly state when-not to use it or list alternative tools beyond the search step.

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, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds valuable behavioral context: the include parameter controls which related data is returned, and the experimental nature with limited event coverage. This goes beyond what annotations provide without contradicting them.

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 three concise sentences, each with a clear purpose: action and return types, experimental warning, and ID acquisition. It is front-loaded and contains no redundant phrasing or filler.

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 a simple getter, an output schema present, and annotations covering safety, the description provides everything needed: purpose, parameter usage, dependency on search_events, and a caveat about data coverage. The return values are covered by the output schema, so no further detail is necessary. It is complete for the tool's complexity.

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 detailed descriptions for event_id and include. The description reinforces the source of event_id and summarizes the effect of include, but does not add significant new meaning beyond the schema. The include enum values are already well-documented in the schema, so the description adds marginal value.

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 action ('Fetch full event detail by OCD event ID') and clearly distinguishes this getter from sibling search tools like openstates_search_events. It also specifies what the tool returns (agenda, participants, media links, documents) when requested via include, making the purpose unambiguous.

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 instruction to 'Obtain the event_id from openstates_search_events' clearly indicates the prerequisite workflow and implies that this tool is for fetching a specific event after search. It also warns about experimental coverage, which is useful context. However, it does not explicitly name alternatives or state when not to use this tool, though sibling getters are for other entities.

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?

Given the annotations already declare readOnlyHint, openWorldHint, and idempotentHint, the description adds valuable context by explaining session format variability and accepted jurisdiction ID formats (OCD, state name, abbreviation). It does not contradict annotations and provides useful behavioral context for expected input flexibility.

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 three sentences, front-loaded with the primary purpose, and each sentence adds value: purpose, usage scenario, and ID format examples. There is no redundancy or wasted words.

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?

The description covers the core purpose, parameter formats, and use case. However, it does not clarify that legislative sessions are only included when the 'include' parameter is specified, which could cause ambiguity about default behavior. Given the presence of an output schema and rich annotations, the description is mostly complete but has a minor gap.

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. The description adds meaning beyond the schema by providing concrete examples of session formats and clarifying accepted jurisdiction_id forms (e.g., 'Washington' or 'wa'), which helps the agent understand parameter usage beyond the raw type descriptions.

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 function: 'Fetch full metadata for a specific jurisdiction including all legislative sessions, their identifiers, and coverage dates.' It uses a specific verb ('Fetch') and resource ('metadata for a specific jurisdiction'), and distinguishes from siblings by highlighting the use case of obtaining session identifiers before bill searches.

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 when-to-use guidance: 'Use when you need to know the exact session identifier for a state before filtering bill searches.' However, it does not mention when not to use this tool or explicitly name alternative tools, so it falls slightly short of a 5.

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?

Beyond the readOnly/openWorld/idempotent annotations, the description adds rich behavioral context: the two-tier structure explained via jurisdiction.classification, the specific pitfall about current_role.org_classification (how a US Senator is 'upper' just like a state senator), and the note about not geocoding addresses. This is exactly the kind of nuance that prevents misinvocation.

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 longer than average but every sentence earns its place: purpose, tiers, classifier distinction, use cases, geocoding caveat, and include hint. It is front-loaded with the core action and tapers into nuance, making it easy to scan.

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 an output schema present, return values don't need explanation. The description covers the tool's main input requirements, behavioral quirks, and usage scenarios comprehensively. It even addresses a likely source of confusion (org_classification vs jurisdiction.classification), which is above and beyond for a typical tool description.

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 already has 100% coverage for all three parameters, so baseline is 3. The description adds value by explaining include=offices for contact info and emphasizing that latitude/longitude must be decimal-degree coordinates (though the schema also says that). The deeper semantic context about jurisdiction.classification vs current_role.org_classification helps interpret results, even though it's not strictly a parameter explanation.

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 starts with a specific verb + resource: 'Find every legislator representing a geographic coordinate'. It clearly states scope (both state and federal tiers) and differentiates from sibling tools by focusing on location-based legislator lookup rather than bills, committees, events, or jurisdictions.

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?

Gives explicit use cases ('constituent-to-representative matching, address-based policy research, electoral boundary analysis') and a critical constraint ('This server does not geocode addresses'). It does not explicitly name alternatives, but the purpose and sibling context make it clear when to choose this over search_people or other tools.

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, openWorldHint, and idempotentHint. The description adds meaningful behavior beyond these: it notes the tool 'returned complete in a single default call' despite pagination, and warns that session formats 'vary widely by state' with concrete examples. It also clarifies that the legislative_sessions include option returns all historical and current sessions, which is critical for correct 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 four sentences, with the core listing activity in the first sentence followed by detail on return metadata, usage context, and session-format variability. Every sentence adds unique, non-redundant information, and the structure front-loads the primary 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?

Given the tool's simplicity (all params optional, read-only, output schema available), the description is complete: it states the full inventory, describes coverage metadata, names the session-discovery workflow, and warns about varying session formats. It also details the include options sufficiently for an agent to invoke 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 input schema covers all parameters at 100%, so the baseline is 3. The description enriches the semantic context by explaining the practical effect of the 'include' parameter (legislative_sessions returns all session identifiers and is 'required when you need to discover valid session values') and by clarifying that the default per_page value fetches and merges pages server-side to return the full 56 jurisdictions in one response.

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 'List all jurisdictions covered by Open States — all 50 states, DC, and 5 US territories', providing a specific verb and resource. It enumerates the exact count (56) and clearly distinguishes from sibling tools by emphasizing the complete collection and its role in discovering session identifiers.

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 states 'Use this when you need to discover valid session identifiers for a state before calling openstates_search_bills with a session filter,' giving a clear context and precondition. It does not mention alternatives like openstates_get_jurisdiction for a single jurisdiction, so it lacks an explicit when-not or alternative 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 declare readOnlyHint, openWorldHint, and idempotentHint, so safety profile is already known. The description adds real behavioral context beyond that: the timeout risk for q-only searches, the reliability benefit of pairing q with jurisdiction, and the effect of include=sponsorships,actions on inline data. Does not contradict 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 somewhat long but every sentence contributes: purpose, required-parameter logic, performance caveat, include guidance, sort tip, and session lookup pointer. It is front-loaded with the core use case and structured information efficiently, though a slightly tighter wording could be possible.

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?

This is a complex tool with 15 parameters and an output schema, but the description covers all critical aspects: required vs optional parameters, performance constraints, related-data include options, sort behavior, and how to obtain valid session identifiers. It gives an agent enough context to invoke the tool effectively without needing additional research.

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% with detailed descriptions for every parameter. The description still adds value by explaining the strategic relationship between q and jurisdiction, warning about timeout, and explaining the practical meaning of sort=latest_action_desc. This goes beyond a simple restatement of schema fields.

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 a specific verb ('Search') and resource ('state legislative bills across all covered US jurisdictions'), and enumerates the major filtering dimensions. This clearly distinguishes it from siblings like openstates_get_bill or openstates_search_committees.

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 required pairing of jurisdiction and q, warns against q-only searches due to timeout, and points to openstates_get_jurisdiction for session discovery. It also gives concrete guidance for include and sort values, which serves as clear when-to-use instruction.

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?

Beyond the readOnly, idempotent, and openWorld annotations, the description discloses critical behavioral traits: upstream timeout risk, experimental status with incomplete data coverage, and the guaranteed presence of a coverageNote field. This is substantial context not available from annotations alone.

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 efficiently packed into four sentences, front-loading the core purpose and mandatory parameter, then providing warnings and usage tips in a logical order. Every sentence contributes unique value without redundancy or fluff.

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 tool's complexity (7 parameters, output schema) and the rich annotations, the description covers the essential context: required scope, experimental caveats, parameter usage examples, and the output field caveat. It is fully sufficient for an agent to select and invoke 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?

Even though the schema has 100% description coverage, the tool description adds practical semantics: jurisdiction is required due to timeout, chamber maps to 'upper'/'lower', classification=subcommittee finds subcommittees, and include=memberships retrieves full rosters. This actionable guidance goes beyond the schema, enriching parameter understanding.

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 'List committees for a jurisdiction,' a specific verb+resource statement that clearly distinguishes this search tool from sibling tools like get_committee or search_bills. It also notes the experimental nature and scope requirements, further clarifying its role.

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 that jurisdiction is required and provides a warning about all-jurisdiction timeouts, instructing users to scope to a single state and pointing to openstates_list_jurisdictions as a helper. It also gives concrete parameter usage guidance for chamber, classification, and include, covering when to use different options.

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 declare readOnly, openWorld, and idempotent, but the description adds valuable context: the experimental nature, that most states lack event data, and that empty results often mean missing data rather than no events. It also explains the scoping constraint and the meaning of include options, going well beyond the structured 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 four sentences, each carrying distinct value: core purpose, jurisdiction constraint/remedy, experimental warning, and filtering guidance. No redundancy or fluff; every sentence 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?

Given the tool's complexity (7 params, 1 required, output schema present), the description covers all critical invocation aspects: required parameter, key filter behaviors, data availability caveats, and interpretation of empty results. The existence of an output schema means return-value details need not be spelled out, making the description complete for agent use.

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. The description enhances parameters by explaining why jurisdiction is required, how after/before are used for date ranges, that require_bills=true is 'most useful for tracking legislation through committee', and that include=agenda,participants provides 'full meeting context'. This adds strategic guidance beyond the schema's field-level descriptions.

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 searches for 'hearings, floor sessions, and committee meetings', which is a specific verb+resource combination. It distinguishes this search tool from the singular openstates_get_event sibling by focusing on the search capability across event types.

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?

It provides clear context: jurisdiction is required, no all-states search, and it explicitly recommends openstates_list_jurisdictions for picking one. It also gives filtering guidance (after/before, require_bills, include) and warns about experimental data coverage. However, it doesn't explicitly contrast with sibling tools like openstates_get_event for single-event lookups.

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?

The description adds substantial context beyond the readOnlyHint/openWorldHint/idempotentHint annotations: timeout constraints for all-state searches, party being unfilterable, org_classification semantics including the merged pagination order and executive exclusion, the exact meaning of omitting org_classification, include option effects, and id resolution behavior (unknown IDs match nothing). No contradictions with annotations; openWorldHint aligns with the 'matches nothing' behavior.

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 dense but well-structured paragraph. It is front-loaded with the primary purpose, then covers required scoping, alternatives, id usage, substring matching, org_classification semantics, and include options. Every sentence conveys necessary guidance without fluff, making it appropriately sized for a tool with 8 parameters.

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 tool's complexity (8 params, 0 required), the description covers all critical operational constraints: jurisdiction/id requirement, timeout mitigation, org_classification behavior, include effects, and id resolution edge cases. With a full input schema, output schema present, and annotations, the description is complete enough for an agent to invoke this tool correctly without further lookup.

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. The description adds value by clarifying cross-parameter relationships: jurisdiction and id are mutually required/exclusive, org_classification omission is not equivalent to 'legislature,' and id resolves multiple person IDs in one call. These nuances go beyond individual schema descriptions, justifying a 4.

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 a specific verb and resource: 'Search state legislators and officials by name, jurisdiction, chamber, or district, or fetch specific people by OCD person ID.' This clearly distinguishes the tool from sibling search tools (bills, committees, events) and from openstates_get_legislators_by_location, which it explicitly names. The scoping and dual search/fetch modes are unambiguous.

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?

Explicit guidance is provided: 'Either jurisdiction or id is required' to avoid timeout; 'Use openstates_list_jurisdictions to pick a jurisdiction, or openstates_get_legislators_by_location when you have coordinates but no state.' It also explains when to use id (IDs from bills/committees) and the nuance that omitting org_classification differs from 'legislature.' This gives an agent clear when-to-use and when-not-to-use direction.

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