Tool Offer Agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Read the canonical machine-readable profile https://tooloffer.kinganlogic.com/manifest.json before calling. Capabilities: Read public API/MCP documentation and retain source-attributed evidence. Collect seller-stated customer, pricing, payment, access and invocation terms. Draft, review and revise an offer within an isolated conversation. Explain the buyer offer and prepare listing guidance without publication. Assess retained offer readiness deterministically without inference or payment. Export structured and human-readable records, with verified multipart retrieval when needed. Drafting is free; operator inference costs and published quotas still apply. Optional FAHCE evaluation is separate and buyer-authorized: 0.15 USDC on Base mainnet via the private human checkout. A free preflight is not an evaluation. Checkout preparation, wallet connection and a 402 challenge are not payment authorization, settlement or a completed result. Changed price, network, token or recipient stops payment. No automatic spending. Source-attributed API/MCP offer intake, conversation, drafting, revision, deterministic readiness assessment and exports. No wallet connection, checkout, FAHCE execution, payment, approval, publication, administration or cross-conversation recovery through this adapter. Release 66979784d826683d48d83d6639e924078a3a3476c3ab488a93a9a57519767f19.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_sessionA | Create an isolated seven-day offer conversation. Requires a unique request_id; replaying it returns the same session. No model inference. |
| send_messageA | Send field: value lines, or a JSON-serialized StructuredIntake object in message, a product question, a revision or a drafting command. Intake keys: tool_url, docs (URL string or 1–3 URL strings), customer, pricing, payment, access, invocation; optional job and seller_name. All other values are strings. Optional schema is TOOL_OFFER_INTAKE_V1. Unknown/duplicate keys and invalid values reject the entire update. Card selections are separate. May use bounded operator model quota. Returns a stable job; optional HTTP Prefer: wait=1 through wait=5 waits without redispatch and may include the signed completed result. Otherwise poll get_result. Never resend uncertain work with a new request_id. No payments or FAHCE execution. May overwrite seller fields or rebuild retained drafts; not read-only. Request-ID deduplication is bounded by retained session/job lifetime, not an unqualified retry guarantee. |
| get_statusA | Ask the existing agent for the current offer status without inference. Returns a job; poll get_result. Does not revise seller terms, but creates a metered asynchronous job and may retain delivery state. |
| assess_offer_readinessA | Deterministic assessment of your retained session without revising seller terms. No fetching, inference, FAHCE, approval or payment. Returns a job, not the report: poll get_result for signed readiness JSON plus full human_readable content, or a resumable report manifest. Not seller certification or commercial clearance. Does not revise seller terms, but creates a metered asynchronous job and may retain delivery state. |
| export_offerA | Export your session's saved offer, proposed plan or explicitly incomplete response without inference. Large responses use the agent's resumable manifest; retrieve each indexed part with get_export_part. An export is not publication or certification. Does not revise seller terms, but creates a metered asynchronous job and may retain delivery state. |
| get_export_partB | Retrieve one existing resumable export part from your session, without inference. Preserve the manifest and verify its hashes; do not claim completion until all parts are received. Does not revise seller terms, but creates a metered asynchronous job and may retain delivery state. |
| get_resultA | Read a job owned by your authenticated client. pending/processing/uncertain is not completion. Poll this same job; do not duplicate an uncertain message. No inference. Polling is metered and may wake queued processing; it is not annotated as a side-effect-free read. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
The tools mostly have distinct purposes: session creation, message sending, status, readiness assessment, export, export-part retrieval, and job polling. However, the set has several async job-producing tools that all funnel into get_result, and get_status versus get_result versus get_export_part may require careful reading to distinguish.
Names consistently use snake_case and a verb-first pattern: start_session, send_message, get_status, assess_offer_readiness, export_offer, get_export_part, get_result. The pattern is predictable and readable throughout.
Seven tools is well within the appropriate range for this workflow. Each tool maps to a meaningful lifecycle step: start, interact, inspect status, assess readiness, export, retrieve export parts, and poll job results.
The core offer-conversation lifecycle is covered, including session start, messaging/intake, status, readiness assessment, export, export-part retrieval, and job result polling. Minor gaps remain around session listing/closure, job cancellation, and explicit session management, but agents can work around them.