Agent continuity audits, referrals, sponsor packets, and Stripe Checkout for Continuum.
Scored across 5 tools
Each tool serves a clearly distinct purpose: creating a checkout, creating a sponsor packet, fetching an offer, registering a referral, and running an audit. There is no overlap between their responsibilities, making misselection highly unlikely.
All tool names follow a consistent verb_noun pattern in snake_case: create_checkout, create_sponsor_packet, get_offer, register_referral, run_audit. The naming is uniform, predictable, and easy to parse for an agent.
With 5 tools, the server is well-scoped for its purpose. Each tool covers a distinct workflow step, and there is no bloat or redundancy. The count fits comfortably within the ideal 3-15 range.
The tool set covers the core lifecycle: creation (checkout, sponsor packet, referral), lookup (offer), and validation (audit). Minor gaps exist, such as no update/cancel for created entities, but the essential workflow appears functional without dead ends.
An api-integration workflow that, after explicit sponsor confirmation of current terms, creates a hosted Stripe URL with all eligible dynamic payment methods. The payer completes payment on Stripe.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_name | No | ||
| sponsor_name | No | ||
| referral_code | No | ||
| sponsor_email | Yes | ||
| terms_version | Yes | ||
| idempotency_key | No | ||
| sponsor_confirmed | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=false, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds context that the checkout is hosted on Stripe and the payer completes payment there, meaning execution continues off-platform. It does not explain the external side effects (e.g., referral activation, potential charge), why retry is safe, or what consuming the idempotency_key means. 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 sentences with no filler. The first carries the precondition and the core effect (creates a hosted Stripe URL), and the second closes the handoff flow. The key decision info is front-loaded, and 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 mutating, outward-facing tool with 7 parameters, zero param descriptions, and no output schema, the description provides the essential flow but leaves operational gaps: how idempotency should be used, how the Stripe URL is returned, and how referral_code/agent_name/sponsor data feed into the session. An agent can invoke it, but must infer call-correctness details from names and schema constraints.
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 0%, so the description must compensate, but it explains none of the seven parameters explicitly. It vaguely maps to sponsor_confirmed and terms_version via 'explicit sponsor confirmation of current terms', yet gives no guidance for sponsor_email, agent_name, sponsor_name, referral_code, or idempotency_key. The const and maxLength constraints in the schema do not convey semantics.
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: 'creates a hosted Stripe URL' with a clear precondition ('after explicit sponsor confirmation of current terms'). This cleanly differentiates it from the siblings (create_sponsor_packet, get_offer, register_referral, run_audit), which operate on different resources and workflow phases.
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 workflow placement: it should be invoked only after the sponsor has confirmed terms, and the payment hand-off to Stripe signals this is the billing step. However, it never explicitly names alternatives, states when not to use this tool, or explains how it relates to the sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
A general-tools sponsor workflow that converts a validated audit into a factual recommendation with the exact published terms.
| Name | Required | Description | Default |
|---|---|---|---|
| audit | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that the output is a 'factual recommendation with the exact published terms,' offering some behavioral context about the result. It does not contradict the annotations, but it does not disclose other aspects like error conditions or prerequisites beyond a validated audit.
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, making it quick to read and process, with the core transformation stated upfront. The phrase 'general-tools sponsor workflow' adds little value and could be removed, but overall the description is appropriately concise and free of redundant 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?
The tool has one nested object parameter, no output schema, and strong annotations, so the description carries most of the functional context. It covers the input (validated audit), the action (conversion), and the output (factual recommendation with exact terms), which is adequate for a basic understanding. It lacks detail about the audit object's contents and the exact meaning of 'published terms,' leaving some gaps.
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 provides zero description for the 'audit' parameter, so the description must compensate. It tells the agent the audit must be 'validated,' which is a useful constraint, but it does not explain the object's structure or required fields. With 0% schema coverage, this minimal hint leaves most parameter meaning undefined.
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 concrete purpose: converting a validated audit into a factual recommendation with exact published terms. It names the input (audit) and output (recommendation), which makes the tool's role clear. However, it does not explicitly contrast it with sibling tools like run_audit or get_offer, and the phrase 'general-tools sponsor workflow' is somewhat vague.
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 phrase 'validated audit' implies the tool should be used after an audit has been run and validated, giving some situational context. There is no explicit statement about when to use this tool versus alternatives, and no exclusions are mentioned. Guidance is only implied, not directly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
A general-tools contract lookup that returns the canonical price, acceptance, delivery, and checkout terms without creating anything.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description adds context beyond this by specifying what the read surfaces (canonical offer terms across price, acceptance, delivery, checkout). The 'without creating anything' wording reinforces rather than contradicts the read-only 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?
A single sentence with no filler. Each clause earns its place: it states the operation, lists the returned term categories, and flags the absence of side effects. The key 'lookup' framing is front-loaded and everything else is directly informative.
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, low-complexity read tool with rich annotations, the description covers the essential decision factors: what it does, what it returns, and that it has no side effects. It omits return-format details and there is no output schema, but that gap is minor for a get-style lookup an agent can safely invoke.
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 and schema coverage is 100% (vacuously), so the baseline of 4 applies. There are no parameters for the description to explain, and it correctly adds no misleading param 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 identifies a specific verb/action ('returns') and a specific resource ('canonical price, acceptance, delivery, and checkout terms'), clearly framing it as a read/lookup operation. The 'without creating anything' clause explicitly differentiates it from the create/register siblings, so an agent can distinguish it without opening any schema.
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 establishes clear context: this is for retrieving offer terms as a pure lookup, and 'without creating anything' implies it is not the choice for creation workflows (which map to the continuum_create_* siblings). It does not name the alternatives explicitly or give when-not conditions, so it stops short of full exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
An api-integration workflow that creates one signed referral link and a provisional noncash Continuum Credits identity; it does not fetch the Agent Card.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_name | Yes | ||
| sponsor_email | Yes | ||
| agent_card_url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate this is not read-only and not idempotent. The description adds useful behavioral detail beyond those flags: it creates exactly one signed referral link and a provisional identity, and explicitly states that it does not fetch the Agent Card. It does not cover side effects like emails or auth requirements, but the annotation layer lowers the burden.
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 core action front-loaded and the negative scope appended. 'An api-integration workflow' is slightly generic, but there is no bloat 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?
For a mutation workflow with no output schema and zero parameter documentation, the description leaves important gaps: it does not explain the return value, the role of each parameter, or how the signed referral link is produced. It also provides no routing guidance among sibling tools.
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 0%, and the description does not explain agent_name, agent_card_url, or sponsor_email. The parameter names are partly self-explanatory, but agent_card_url is not connected to the 'signed referral link' mechanism and sponsor_email's role is left unstated. The description fails to compensate for the missing schema docs.
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 ('creates') and identifies the exact resources produced: 'one signed referral link' and 'a provisional noncash Continuum Credits identity.' The clarifying negative, 'it does not fetch the Agent Card,' helps distinguish this tool from related 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?
There is no explicit guidance about when to use this tool versus continuum_create_checkout, continuum_create_sponsor_packet, continuum_get_offer, or continuum_run_audit. The intended usage is implied only by the title 'Register a provisional referral' and the description's action, with no conditions, prerequisites, or exclusions stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
An observability readiness audit that scores eight self-declared continuity capabilities without fetching evidence or invoking a model.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_name | Yes | ||
| categories | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already indicate readOnly and idempotent behavior, and the description adds that it does not fetch evidence or invoke a model, reinforcing the non-destructive, side-effect-free nature. This goes beyond the annotations by clarifying the absence of external calls and model inference, which is valuable for an agent deciding whether to use it.
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, compact sentence with no redundant words. It efficiently communicates the core function and key constraints (self-declared, no external fetching, no model invocation) without any 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 provides sufficient context for an agent to understand the tool's purpose and limitations, especially given the schema details. It does not describe the output format or scoring methodology, but since there is no output schema, and the tool's behavior is straightforward, the description is reasonably complete for typical 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?
The description alludes to the 'categories' parameter by mentioning eight capabilities, but it does not explain the purpose of 'agent_name' or the meaning of the 'level' and 'evidence_url' sub-fields beyond what the schema already shows. The self-declared aspect is hinted at, but parameter semantics are only partially enriched.
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 performs an observability readiness audit that scores eight self-declared continuity capabilities. It distinguishes itself from sibling tools (e.g., checkout, sponsor packet) by being an audit, so an agent can easily identify its purpose.
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 useful guidance by stating that the audit is based on self-declared capabilities and does not fetch evidence or invoke a model. This implies it is a lightweight, non-verifying check, suitable when quick assessment is needed. It doesn't explicitly contrast with alternatives, but the nature of the operation is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
continuum_create_checkoutcontinuum_create_sponsor_packetcontinuum_get_offercontinuum_register_referralcontinuum_run_auditAgent-native commerce with trusted catalog, durable carts, and Stripe Checkout via MCP and UCP.
Agent Commerce MCP — agent-native A2A storefront. Discovery, Stripe checkout, affiliate program.
AI agent recruiting: talent pool match, reference checks, credit packs via Stripe MPP
Agent Commerce Protocol MCP — bridges Stripe ACP + Google AP2 + Coinbase x402 for agent payments
Add one secure layer between your agents and this server.
