HokAI

buy_guide_spot

Buy a labelled Sponsored spot for a product in one Hokai guide. Returns
checkout_url, a Stripe card payment page. The dates are held for 30
minutes while it is open; the first payment wins.

Rule to pass on to the vendor: guide spots are pay first. The entry is
written by hand and goes live within 48 hours of payment, or on the start
date if that is later. If the guide does not suit the product, Hokai moves
the spot to a guide that does. Refunds are not automatic: ask
damien@hokai.io.

Give the product EITHER as product_slug (+ product_type) when it already
has a Hokai page, OR as product_name + product_url when it does not (its
page is then written free and the earliest start is a week out).

Args:
    email: a work email for the vendor
    guide: the guide's slug, from vendor_catalog (guides[].slug)
    product_slug: the product's Hokai slug, e.g. "notion-ai" (optional)
    product_type: tools, agents, skills, models, companies or services
    product_name: the product's name, when it has no Hokai page (optional)
    product_url: the product's website, when it has no Hokai page (optional)
    starts_on: YYYY-MM-DD (optional; default is the guide's next free day)
    months: 3, 6 or 12
    company: company name (optional)
    agent: your agent's name (optional)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "email": "<email>",
      "guide": "<guide>"
    },
    "name": "buy_guide_spot"
  }
}

Input Schema

Name	Required	Default
`agent`	No
`email`	Yes
`guide`	Yes
`months`	No
`company`	No
`starts_on`	No
`product_url`	No
`product_name`	No
`product_slug`	No
`product_type`	No	tools

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 10, 2026

TDQS

A4/5.0

Behavior3/5

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

Because no annotations exist, the description carries the full burden, and it does disclose returns (checkout_url / Stripe payment page), the 30-minute date hold with first-payment-wins semantics, manual entry within 48 hours, guide substitution if unfit, and non-automatic refunds. What it omits is equally relevant for a purchase tool: there is no price, currency, or cost indication anywhere, and no auth or permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with what the tool does and returns, then splits vendor-facing rules from arguments, which suits a 10-parameter tool. A few clauses are looser than needed ('The entry is written by hand', the blockquote-style rule framing), but nearly every sentence carries operational information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, unannotated, no-output-schema purchase tool this is unusually complete: it covers the return value, timing, hold mechanics, substitution policy, and refund path. The notable gap is commercial context — an agent cannot tell the buyer what a spot costs or what currency is charged before invoking.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must supply all meaning, and it does: it documents every one of the 10 parameters, gives an example slug, spells out the product_type value set (tools, agents, skills, models, companies or services) that the schema does not enforce as an enum, and constrains months to 3, 6 or 12. It also clarifies a required-ness the schema hides, stating the product must be supplied one way or the other even though those params are marked optional.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening states a specific verb and resource: 'Buy a labelled Sponsored spot for a product in one Hokai guide.' The scoping ('one guide', 'Sponsored spot') makes it distinguishable from listing- or lead-purchase siblings in practice, but no sibling is named, so differentiation is inferred rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit conditional guidance for the two mutually exclusive product modes (product_slug + product_type versus product_name + product_url) and their differing earliest start dates. What it does not do is say when to choose this over buy_leads or buy_listing, so guidance is strong on internal choices but silent on external alternatives.

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

All HokAI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?