Start Companies LLC Formation

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

Annotations are minimal (readOnlyHint false, etc.), so description carries the burden. It discloses that the tool registers the request, sends an email with reference, returns a payment link, and that Start Companies replies within 24 hours. It does not discuss idempotency or error states, but covers core behavior well.

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?

Four sentences with no fluff. The first sentence encapsulates the main purpose and outputs. Subsequent sentences add precise usage constraints and post-call expectations. 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 9 parameters (7 required) and no output schema, the description covers the key actions, preconditions, and a downstream expectation. It lacks details on return value format or error cases, but for a form submission tool it is substantially 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 coverage is 100% with individual parameter descriptions, so baseline is 3. The description adds meta-context that 'everything was captured here' (reassuring completeness) and links 'paquete' to package confirmation, but does not explain individual parameters beyond schema. Adequate.

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 registers an LLC formation request, sends a confirmation email, and returns a payment link. It distinguishes from sibling tools (all read/info tools except start_itin_application) as the creation action, and specifies the prerequisite of explicit package confirmation, differentiating from recommend_llc_package.

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 'Call this ONLY after the user has explicitly confirmed the package.' Also advises handing off to a person if not ready to pay, providing clear when-to-use and when-not-to-use guidance. Though it doesn't name sibling alternatives, the precondition is 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?

The annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe, read-only operation. The description adds behavioral context by noting that passing a reference number matches payment to a prior request, which is beyond what annotations 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?

The description is three sentences, front-loaded with the core purpose, and every sentence adds distinct value: purpose, usage guidance, and reference parameter context. No extraneous information.

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 or nested objects, and schema covers all parameters, the description is mostly complete. Minor gap: it doesn't mention that the user must have an existing lead or request to get a link (implied for the 'referencia' case, but not explicit for initial payment when no reference is passed).

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 covers all parameters with descriptions (100% coverage). The description adds marginal value by explaining that 'referencia' should be a reference from 'create_llc_lead' and describing the enums implicitly, but the schema's enum and property descriptions are sufficient.

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 tool as returning a Stripe checkout link for three specific packages, distinguishing it from siblings like 'get_order_status' and 'get_renewal_info'. The verb 'Returns' and resource 'checkout link' are specific and 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 explicitly states when to use this tool ('user already knows which package they want and wants to pay now' or 'submitted the request earlier and wants to pay afterwards'), and implies when not to use it (e.g., when user needs a recommendation, which would go to 'recommend_llc_package'). It also provides guidance on passing a reference number if available.

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 establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds meaningful behavioral context beyond those annotations by explicitly confirming that it doesn't submit or start an application, and by clarifying that the tool returns a link rather than performing a transaction. No contradiction with annotations exists.

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 a clear front-loaded 'Returns...' statement. The subsequent sentences add differentiation and usage context, so each sentence earns its place. It is concise without being terse, and well-organized for a quick agent read.

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 fully enumerates what the tool returns: definition, cost, documents, IRS timeline, and application link. It also covers the limiting behavior and the exact queries that should trigger this tool. For a simple informational read-only tool with one optional parameter, nothing needed for correct invocation is missing.

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 description for the single 'socios' parameter is complete and self-explanatory: it states how many people need an ITIN and that it is used to quote the total. The tool description does not add detail about this parameter, but with 100% schema coverage, the structured field already carries the semantic burden.

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 ('Returns') and names a clear resource: information about ITIN, its cost, required documents, IRS processing time, and the application link. It also explicitly differentiates itself from application-creating tools by stating it does not submit or start an application, and the 'Use it when...' clause reinforces its distinct role among siblings.

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 explicit use triggers: user asks about ITIN, tax ID, taxpayer number, or filing as a multimember LLC member. It also states a when-not condition ('does not submit or start an application'), though it does not name an alternative sibling tool to route to, so it stops short of a fully explicit alternatives mapping.

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=false, so the safety profile is well covered. The description adds the scope of the returned data (three packages plus add-ons, renewals, tax advisory) but does not add deeper behavioral details like pagination or data freshness, which would be expected if absent. Given the strong annotations, this is adequate but not exceptional.

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 sentences with no wasted words. The first sentence efficiently lists the content scope, and the second provides a direct usage directive. Information is front-loaded and each 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 zero-parameter, read-only retrieval tool, the description fully covers what the agent needs to know: what data is returned, and when to call it. There is no output schema, so the description's content summary suffices. Combined with thorough annotations, nothing critical is missing.

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 is empty, so there are no parameters to document. The description successfully compensates by explaining what the tool returns, giving the agent a clear mental model of the output. Per the rubric, 0 parameters warrants a baseline of 4, and the description meets that expectation.

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 the three US LLC formation packages and lists exactly what data is included: price, turnaround time, inclusions, add-on services, annual renewals, and tax advisory. This is specific and distinct from siblings like get_renewal_info or recommend_llc_package, making the tool's 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 description explicitly instructs to call this tool before discussing prices, renewals, advisory, or inclusions, which is clear contextual guidance. However, it does not explicitly name alternatives or state when not to use it, leaving room for an agent to infer the contrast with recommend_llc_package.

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, so the safety profile is covered. The description adds useful behavioral context beyond annotations: the email is a second factor, not a search key, and the call returns status only, not personal data.

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, and the most important operational guidance (requires both fields, ask the user) is front-loaded. Every sentence contributes actionable information.

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, two-parameter read-only lookup with no output schema, the description gives enough information to call correctly: what to collect, what it returns, and what it does not return. It could be slightly stronger by describing possible status values or not-found behavior, but this is not essential for invoking the 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?

The schema already describes both parameters with 100% coverage, so the baseline is 3. The description adds meaningful context by clarifying the reference number format (SC-MMDD-XXXX) and explicitly framing the email as a matching factor rather than a lookup key, which helps the agent collect and use the arguments correctly.

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 ('Looks up'), a specific resource ('a previously submitted LLC formation request'), and the result ('returns its status'). This clearly differentiates it from sibling tools like create_llc_lead or get_renewal_info by anchoring on an existing request's status lookup.

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 caller to ask the user for both the reference number and email before calling, and explains that both are required. It does not name alternatives or when-not-to-use scenarios, so it falls just 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?

Annotations already mark the tool as readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds valuable behavioral context beyond that: it explains that the tool does not sell renewals and that the user is referred to the team via WhatsApp, email, or the client portal. This tells the agent what to do with the returned information rather than just declaring it safe.

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 front-loaded with the core answer ('Returns what the annual LLC renewal costs and covers'), then adds the sales-channel caveat, then a useful trigger list. It is slightly longer than strictly necessary, but each sentence contributes meaningful guidance for tool selection and invocation.

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 informational tool with two optional parameters and no output schema, the description covers the return subject matter, the usage triggers, and the follow-up referral path. It does not specify an exact response format, but that is acceptable given the absence of an output schema and the low tool 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%, so the schema already documents both parameters ('estado' and 'multimember') adequately. The description adds some context by mapping the multimember case to Form 1065, but it does not substantially enrich parameter understanding beyond the schema, so a baseline 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 states a specific verb and resource: it 'Returns what the annual LLC renewal costs and covers', including concrete IRS forms. It also clearly distinguishes itself from sales-related sibling tools by explicitly saying renewals are not sold through this server, leaving no ambiguity about the tool's 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?

Gives an explicit trigger list: 'Use it when the user asks about renewing, keeping the LLC active, IRS filings, penalties, the annual report, the state fee, or what happens after the first year.' It also clarifies the referral workflow when a user wants to actually purchase a renewal. It does not name specific alternative sibling tools, but the trigger list is specific enough to route an agent correctly.

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 'Read-only: it does not create anything,' which reinforces the annotation but provides no additional behavioral depth such as response format, potential errors, or limitations. With annotations present, this does not go beyond the minimum.

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 sentences, front-loads the core purpose and inputs, and explicitly notes the read-only nature. Every sentence contributes useful information without redundancy or filler, making it highly concise 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?

The description gives a high-level summary of inputs and output, but the schema lists zero required parameters, which conflicts with the description's implication that the US state and membership are always needed. It also does not clarify what constitutes a 'package' or what happens with partial inputs, and no output schema exists to fill this gap. The presence of sibling get_llc_options further suggests that more usage context would be valuable.

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 each parameter is already documented in the input schema. The description only summarizes the parameter classes (state, membership, services) without adding any new meaning about formats, defaults, optionality, or interdependencies. It meets the baseline but adds no value beyond 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?

The description clearly states the tool's function: it recommends an LLC package based on US state, membership count, and needed services, and explains why. However, it does not explicitly differentiate itself from the sibling get_llc_options tool, which likely also deals with package selection, so it misses the additional clarity that naming a sibling would provide.

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 usage by specifying the required inputs ('Given the US state, whether the LLC has more than one member, and which services the user needs'), but it provides no explicit guidance on when to choose this tool over alternatives like get_llc_options, and does not mention any exclusion conditions or fallback paths.

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