California Insurance

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds useful behavioral context by naming exactly what data is returned and by specifying the required credential. It does not disclose error handling for invalid keys, but for a read-only status tool this is a minor gap and there is no contradiction with 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 a single sentence with the scope and key prerequisite front-loaded, followed by a compact list of returned fields. There is no filler or redundant content. The list is slightly dense but remains readable and information-dense.

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 one-parameter, read-only tool with rich annotations, the description is mostly adequate. It enumerates the return fields and the required key. However, domain-specific terms such as 'rail', 'terms', and 'states' are left unexplained, and with no output schema the agent may not fully understand the semantics of the returned data.

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 for the single parameter buyer_key is 100%, so the baseline is 3. The description's 'Requires the buyer key issued at confirmation' mostly duplicates the schema's 'Issued to the licensed contact at confirmation'. It adds no real format, validation, or usage detail beyond what the schema already provides.

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 explains that the tool reports status for a registered agency and enumerates the returned attributes: states, rail, terms, founding period, queued/delivered counts, credit balance, and licence verification. It lacks an explicit action verb such as 'retrieves' or 'gets', but the title and 'For a registered agency' make the purpose clear. It also differentiates from siblings by requiring the buyer key issued at confirmation.

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 states a clear prerequisite: the agency must already be registered and the caller must have the buyer key issued at confirmation. However, it gives no explicit guidance on when to choose this tool over siblings like check_eligibility, register_agency, or pull_requests, and no when-not-to-use exclusions. Usage context is implied rather than explicitly routed.

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, idempotentHint, and destructiveHint, covering the safety profile. The description adds valuable behavioral context: it names the exact return content (licensed states, permitted actions, licensed agent counts) and the privacy-sensitive placement of the call. This goes beyond what annotations alone provide.

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 tightly written sentences with no filler. The core purpose is front-loaded, the usage directive ('Call this first') is immediate, and the return summary is compact. 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?

For a simple read-only tool with two parameters and rich annotations, the description covers purpose, timing, and return payload. The only notable gap is ambiguity about whether the response is scoped to the requested state or lists all licensed states, which could affect an agent's expectations of the output.

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 50%: the state parameter is documented, but product relies only on its enum and default. The description reinforces the meaning of state by tying it to the eligibility check, but it does not clarify the product parameter or its role. This partial compensation merits a mid-range score.

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 ('Check') and identifies the resource ('return quotes for a state') and its boundary ('before any personal details are collected'). It clearly conveys the tool's purpose, but it does not explicitly distinguish this tool from sibling tools such as agency_status or get_quotes, relying instead on the unique pre-collection angle.

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 'Call this first' provides clear ordering context, and the phrase 'before any personal details are collected' sets the intended use case. However, it does not explicitly state when to avoid this tool or recommend an alternative sibling, so it stops short of full when/when-not 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. The description adds useful behavioral context by listing what information the tool exposes and noting that it is machine-readable so the exchange can be evaluated before it occurs. No contradiction with 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 dense sentences with no filler. The first sentence front-loads all the content dimensions, and the second explains the practical value of the machine-readable format. 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?

For a zero-parameter, read-only tool with no output schema, the description sufficiently covers what to expect, when to call it, and why it is useful. The only minor gap is the precise output format, but 'machine readable' reasonably communicates that the result can be programmatically evaluated.

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 tool has zero parameters, so schema description coverage is effectively 100% and there is no parameter documentation burden on the description. The baseline of 4 applies since there is nothing for the description to add about parameter meaning.

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 resource — data use terms and consent wording — and enumerates the specific dimensions it covers: recipients, purpose, retention, revocation, and consent text. It distinguishes itself by anchoring to request_agent_contact, which is present in the sibling list. It lacks an explicit verb like 'get' or 'retrieve', but the function is 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 description states precisely when to use the tool: before calling request_agent_contact, to obtain the exact consent wording and evaluate the exchange. It gives a clear usage context and rationale. It does not discuss exclusions or when to prefer other siblings, but the specific trigger condition is explicit.

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 and destructiveHint=false, but the description adds valuable behavioral detail: licensing limitations, no PII requirement, quote_id registration for unlicensed scenarios, and the server's iterative request for missing facts. It goes well beyond the structured annotations and paints an accurate picture of the tool's runtime 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 three sentences with no filler. The primary purpose is front-loaded, followed by the PII constraint, the licensing fallback, and the missing-facts behavior. Every sentence conveys a distinct and useful fact, making it efficient and well-structured.

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 has no output schema and 10 parameters, the description covers the key invocation requirements and expected outputs well: prices when licensed, quote_id when not licensed, and interactive fact-filling. It could be more complete by describing the response shape for the licensed case, but the essential behavior for correct invocation is present.

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 only 20%, so the description must compensate, but it only explains the general principle that parameters are 'rating facts only' and that PII is not required. It does not clarify individual parameters such as vehicle_make_model format, annual_mileage units, or prior_continuous meaning. The required fields like garaging_zip, date_of_birth, and vehicle_year receive no additional semantic 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 states a specific verb and resource: 'Return indicative auto insurance prices from multiple carriers.' It also specifies a scope condition ('where this entity is licensed to show them'), which clearly differentiates this tool from siblings like check_eligibility or market_data. The purpose is immediately recognizable and not a tautology.

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 context for when to call the tool: when an indicative auto insurance price is needed, using only rating facts and no PII. It also explains the fallback when not licensed. However, it does not explicitly mention alternatives or when not to use this tool versus a sibling such as check_eligibility or market_data, so the routing guidance is incomplete.

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?

Well beyond the readOnlyHint, the description discloses de-identification guarantees, data fields, per-record pricing with a minimum, required payment methods, and the exact failure mode (402 with price and preview count). It also points to /data.json for a concrete sample and schema. No contradiction with 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 dense but every sentence earns its place: dataset contents, privacy guarantee, filter and pagination controls, payment behavior, and a schema link. It is front-loaded with the most important identification of the resource.

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 an 11-param tool with no output schema, this is nearly complete: it explains the record fields, privacy, filters, pagination, payment, failure mode, and where to get the schema. It does not spell out exact date formats or min pull amounts, but the /data.json pointer mitigates that 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?

With only 36% schema description coverage, the description carries the parameter load. It names the filter parameters (state, since, until, door, vendor), pagination (limit, offset), and maps payment params to methods (prepaid buyer key, x402, MPP, AP2). It does not give date/state/door value formats, but compensates for sparse schema better than most tools.

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 title names a specific verb ('Buy') and resource ('de-identified demand records'), and the description specifies the exact dataset contents: auto insurance requests with fields like age band, ZIP3, vehicle, coverage, and outcome. This clearly distinguishes it from siblings like get_quotes or check_eligibility, which concern different resources.

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 operational context: filter by state, since, until, door, and vendor; use limit and offset; pay with buyer_key, x402, MPP, or AP2; and expect a 402 without payment. It does not explicitly compare against sibling tools, but the resource and workflow are unambiguous enough for an agent to select it when purchasing demand data.

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 goes well beyond the annotations by explaining the x402 payment requirement for metered buyers, the 402 status with accepts[], and the access-scope guarantee. It also implies a non-idempotent, state-changing operation consistent with readOnlyHint=false and idempotentHint=false. No contradiction with 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?

Three dense sentences deliver the core action, authentication requirement, payment caveat, and data-scope guarantee without wasted words. The most important operational detail ('Drain the queue') 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 the lack of an output schema, the description adequately covers the main response concept ('Records are projected to the scope...'). It could add what happens on an empty queue or when the buyer key is invalid, but these are not essential for selecting and invoking 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?

Schema description coverage is 75%, so the schema carries most parameter meaning. The description adds context for the payment parameter via the x402 requirement and states that the buyer_key is required, but it does not explain the mandate or credential parameters beyond their schema 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 uses a specific verb ('Drain') and resource ('queue of pool records routed to you'), and the title adds 'buyers' to clarify the intended actor. This clearly distinguishes it from the sibling tools, none of which describe pulling routed records.

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 makes the usage context clear: it is for buyers retrieving routed pool records and requires the buyer key. It does not explicitly name alternative tools or state when not to use it, but none of the siblings are close alternatives, so the guidance is adequate.

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 goes beyond the annotations by disclosing that the contact must confirm via an email link, that nothing is delivered before confirmation, and that there is a founding period with free leads followed by prepaid credits. These are important behavioral traits that are not captured in the annotations, and they are clearly stated.

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 concise and well-structured. The first sentence states the purpose, the second lists the required inputs, the third explains the confirmation and delivery timing, and the fourth covers the pricing model. It front-loads the key purpose and avoids unnecessary fluff, making it easy to parse.

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 aspects of registration: inputs, confirmation process, delivery timing, and pricing. It also points to /join for terms, which adds completeness. However, it does not mention the optional verify_token parameter or what the response/next steps are after registration. Given the tool's complexity and lack of an output schema, this is a minor gap, so a 4 is appropriate.

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 description summarizes the required fields (agency name, NPN, state, appointment states, contact info, delivery method) and relates them to the registration flow, but it does not add significant new meaning beyond the existing schema descriptions. For parameters without descriptions (e.g., agency_name, website, webhook_url), the description does not provide additional clarity. It adds moderate value by grouping the fields but does not deeply enhance 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 clearly states the tool's purpose: to register an agency to receive consented consumer requests in its states. It identifies the specific action (register), the resource (agency), and the context (for an AI working for a licensed agency). This differentiates it from sibling tools like check_eligibility or get_quotes.

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 implies the tool is for agency registration when the AI is acting on behalf of a licensed agency, and it notes the confirmation requirement and delivery timing. While it does not explicitly say 'use this instead of X', the context makes the appropriate use case clear, and the sibling tools are obviously different. It could benefit from stating when not to use it (e.g., if already registered), but the guidance is sufficient.

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?

Discloses meaningful side effects beyond the annotations: up to 4 agents receive the request, scopes control marketing-partner sharing, consent is mandatory, every delivery/refusal is receipted, and revocation happens via POST /forget. 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 dense but well organized: main action, prerequisites, consent mechanics, scope, and revocation. Every sentence adds necessary operational or compliance information without 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?

For a consent-gated tool with no output schema, the description covers the essential invocation path and important side effects. Minor gaps remain around optional fields and the exact consent elicitation URL flow, but overall it 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?

With schema coverage at 44%, the description compensates by explaining quote_id's origin, the consent requirement and its modes, the verified phone's effect on price/priority, and street_address's purpose. Some optional parameters like best_time, email_address, and preferred_channel are not addressed, but the key required parameters are well contextualized.

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—connecting the consumer with licensed agents who can quote and bind—and identifies the required prerequisite (quote_id from get_quotes). This clearly sets it apart from sibling tools like check_eligibility and register_agency.

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 concrete prerequisites (quote_id, name, phone, explicit consent) and explains acceptable consent paths. It does not explicitly name exclusions or alternatives, but the usage context is strong and actionable.

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