My Insure Bank (MIB)

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

With no annotations, the description carries the burden of disclosing behavior. It clearly conveys that this is an informational tool with no data mutation or complex side effects. It does not explicitly state what the response format looks like, but for an 'about' tool the implied read-only nature is sufficient.

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, front-loaded sentence that efficiently covers the three key topics. Every clause adds meaningful value with 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?

Given the tool's simple nature (0 parameters, no output schema, no nested objects), the description is fully complete. It covers what the tool is, what it explains, and the target audience, which is everything an agent needs to invoke it appropriately.

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 parameter semantics are not applicable. The baseline score for 0-param tools is 4, and the description needs to add no parameter-level detail.

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 clear informational scope: what MIB is, what the server does, and how to get an API key. This fully distinguishes it from the transactional sibling tools like list_insurance_products or compare_insurance_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 an onboarding/orientation resource and explains the developer integration path. It does not explicitly state 'use this before other tools' or name alternatives, but the context makes the usage scenario unambiguous.

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 discloses behavioral traits: real-time data, presence of buy_url for non-motor, deliberate omission for motor, and the mandatory post-quote workflow. It also reveals that motor offers include a to_buy field to collect customer details. This is transparent about the tool's side effects and obligations.

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 yet efficient. It opens with the core purpose, then delivers the critical motor-workflow exception, and finally lists rating inputs per product type. Every sentence carries essential information with no filler. Despite its length, it remains well-structured and 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 tool's complexity (10 parameters, 4 product types, no output schema), the description covers all necessary aspects: real-time quote retrieval, buy_url for most products, the motor exception with required follow-up, and the specific parameters needed per product. It also references the to_buy field without relying on an output schema. This makes the description self-sufficient for correct tool invocation.

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 provides 100% coverage with parameter descriptions. The description adds value by consolidating which parameters are required for each product type (e.g., auto → sum_insured + cover_type) and clarifying the meaning of sum_insured for different lines. While it largely repeats schema info, the structured mapping aids correct usage beyond the raw schema, justifying a score above baseline.

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: retrieving real-time insurance premiums across multiple partner insurers in NGN. It specifies the resource (partner insurers) and the action (get premiums), and differentiates from sibling tools like get_buy_link by explicitly describing when that tool is needed. The mention of product types further clarifies scope.

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 usage guidelines, including when to use this tool (to get quotes) and the required follow-up for motor quotes (must ask for vehicle/address/NOK details and call get_buy_link). It also explains how rating inputs vary by product type, effectively guiding the agent on parameter selection. This distinguishes it clearly from get_buy_link and other siblings.

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?

No annotations are provided, so the description carries the burden of behavioral disclosure. It discloses that the tool errors if prerequisites are missing, that the customer lands on a review summary, and that the agent never handles payment. It could further state the return format or side effects, but for a checkout-link builder the disclosed behavior is substantial.

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: what it builds, hard prerequisite with failure mode, and what the customer/agent experience is. Front-loaded with the purpose, then the most critical constraint, then the payment context. No fluff or 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?

The tool has 10 params and nested objects, but the schema covers them well and the description ties them to upstream tools. With no output schema, the description could clarify the return payload more, but it explains the customer-facing outcome well enough. Missing explicit return-structure docs is the main 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 90% and the schema already describes each parameter. The description adds context beyond schema: it explains which parameters come from get_purchase_requirements and emphasizes that vehicle/insured/next_of_kin are required collectively even though they're not marked required in the schema. This compensates for the schema's shallow 'required' list.

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 what the tool does: 'Build the MIB hosted-checkout link for a chosen offer (from compare_insurance_quotes).' It specifies the verb (build), the resource (hosted-checkout link), and the precursor (offer from compare_insurance_quotes), which also distinguishes it from sibling tools like get_purchase_requirements or compare_insurance_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?

It explicitly says when to use: with an offer from compare_insurance_quotes, and only after get_purchase_requirements has collected full details. It even warns that without those details the tool returns an error telling you what to collect, effectively providing a when-not-to-use condition. This is clear contextual 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?

With no annotations, the description carries the full burden. It discloses what data is included (vehicle details, address, next of kin) and what is excluded (identity). It also explains the downstream behavior (prefilled checkout page). It does not explicitly state that the tool is read-only, but the nature of 'get' and the phrasing imply it is non-mutating.

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 two-sentence block that front-loads the core purpose. Every sentence adds value, from the list of fields to the workflow instruction to the identity exclusion. It is longer than the typical one-liner but appropriately sized given the need to convey both the return content and a usage sequence.

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 tool with one parameter and no output schema, the description is quite complete. It tells the agent what the tool returns (a list of required data), how to use the result (call get_buy_link), and a boundary (identity is never collected). The lack of explicit output schema is mitigated by the enumeration of fields, at least for motor, which sets expectations for other product types.

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 has zero coverage for the product_type parameter, so the description must compensate. It provides an example for 'motor' with a full list of fields, indicating that requirements vary by product type. However, it does not explain what to expect for health, travel, or gadget, leaving the agent to infer that the structure is analogous. This is some compensation but not complete.

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 that the tool returns the data items collected by MIB's purchase forms, with a detailed example for motor. It distinguishes itself from siblings by focusing on 'purchase' rather than 'quote' and by explaining how it feeds into get_buy_link. However, it does not explicitly contrast itself with get_quote_requirements, so it misses full sibling differentiation.

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 tells the agent when to use the tool: collect all listed data in chat, then call get_buy_link with it. It also provides a clear exclusion: 'Identity (DOB/NIN) is never collected in chat.' This gives strong guidance on placement in the workflow and alternatives implicitly.

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?

Although no annotations are provided, the description fully explains the tool's behavior—it returns details and implies a read-only operation with no side effects, and even outlines the workflow with the subsequent tool.

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, well-structured, and includes purpose, usage order, and parameter handling in two sentences without unnecessary 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?

The description is self-contained and provides sufficient context for an agent to understand when and how to use the tool, including its relationship to compare_insurance_quotes, without needing additional explanation.

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 single parameter product_type is fully described in the schema with an enum and explanation of omission, and the description reinforces this, covering all parameter nuances.

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 returns details to collect from the customer for a line of insurance, distinguishing it from sibling tools like compare_insurance_quotes and list_insurance_products.

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 instructs to call first and then use the output with compare_insurance_quotes, and explains the effect of omitting product_type, providing clear when-to-use 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?

With no annotations, the description carries the transparency burden. 'Browse the live product catalogue' does imply a read-only operation against current data, and the one-insurer scope is disclosed. But it doesn't mention response format, pagination, ordering, access requirements, or any other behavioral details.

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 two short sentences, front-loads the core action, and includes only useful details. Every phrase adds value, and there is 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?

Given the low complexity—two parameters, both enum-based, no output schema—the description provides enough context for a basic list operation. It covers valid inputs and the key filtering rule, though a note about what the returned catalogue looks like would make it slightly more 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?

The schema already provides enums for insurer and line, but the description adds meaningful conditionality: it tells the caller that the line filter applies specifically to emPLE and can be 'general' or 'life'. It also repeats the insurer values in a natural-language way, compensating for the schema's 50% description coverage.

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 action—browse/list the live product catalogue MIB carries—and identifies the resource as products for a single insurer. It distinguishes itself from quote/comparison siblings by focusing on the product catalogue, though it doesn't explicitly name those alternatives.

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 a clear context—use this when you want to browse products for one insurer—and adds the emPLE line-filter guidance. However, it doesn't explicitly say when not to use this tool or point to sibling tools for quote comparisons, so the usage guidance is implied rather than 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?

With no annotations, the description carries full responsibility for behavioral disclosure. It transparently states that MIB's licensed brokers may follow up to help the customer switch, and it instructs the agent to ask for consent before calling. It also notes the output (estimated annual saving). This covers key side-effects and consent requirements, though it doesn't detail data handling or potential errors.

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 composed of three sentences, each earning its place: the purpose, the mechanism and output, and the follow-up/consent requirement. It is front-loaded with the purpose and stays focused. It's slightly longer than strictly necessary, but all content is relevant and no redundancy exists.

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 tool with 8 parameters and no output schema, the description effectively covers what the tool does, what it returns (estimated annual saving), and its side-effect (possible broker follow-up). It also highlights the consent requirement, which is critical for compliance. It doesn't describe error cases or API-specific behavior, but the core information is sufficient to 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?

The schema has 100% description coverage for all 8 parameters, so the baseline is 3. The description reinforces that name and phone are required and explains why phone is needed (for broker follow-up), but it doesn't add substantial meaning beyond what the schema already provides. The tool's purpose gives context for all parameters, but the schema is already quite descriptive.

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: a free second opinion on an existing insurance policy, comparing current premium to live market rates and reporting estimated annual savings. It distinguishes itself from the sibling compare_insurance_quotes by focusing on existing policies held by the customer with any insurer, making the scope explicit.

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 implies when to use the tool: for policies the customer already holds, not new business. It provides context about requiring consent and potential follow-up, but it doesn't explicitly name alternatives or state when not to use it. The context is sufficient to guide selection, though an explicit exclusion would strengthen it.

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