Skip to main content
Glama

AI Agent Offer

ai_offer

AI Agent Offer: one offer for the people ChatGPT, Claude and Perplexity send, said the same to people and agents. With nothing: the AI-sent visits of the last 28 days by engine with their conversions, whether a landing line is worth testing yet (10 AI-sent visits in 28 days), the founder's offer if kept, whether one shipped, referralScript (a browser expression naming the assistant that sent the visit, or null), the offer page's Markdown and its schema.org Offer once the offer is set, and the rules (never content for bots only). With save: the founder's offer (kind credit, discount, trial or other; what they get, in their words; apply auto or code; the code; an end date). Free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ai_offer"
  }
}

Input Schema

NameRequiredDescriptionDefault
saveNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.5/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false, destructiveHint=false, openWorldHint=true; they cannot express that this tool is a read when called bare and a mutation when called with save, and the description makes that explicit. It also adds concrete operational context: the 10-AI-visit-in-28-days test threshold, the "never content for bots only" rule, and that the offer is echoed back to people and agents identically. Return-shape and pagination detail are absent, hence not a 5.

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

Conciseness3/5

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

The "With nothing / With save" framing imposes useful structure and every clause does carry information, but the whole definition is one sprawling run-on sentence with nested lists that is slow to parse. A bulleted return list and a separate save paragraph would preserve content with far less reading cost.

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 single-parameter tool with a nested object, no output schema, and annotations that only cover safety, the description supplies the return contents (per-engine visits and conversions, test-readiness verdict, founder's offer, referralScript behavior, page Markdown and schema.org Offer), the write payload, and the governing rule. Only input validation limits and referralScript's exact consumption model remain thin.

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

Parameters4/5

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

Schema description coverage is 0% for the one nested parameter, so the description carries the burden and largely succeeds: it enumerates kind (credit, discount, trial, other), what ("in their words"), apply (auto or code), the code, and an end date, which maps onto every nested field including endsAt. It omits the schema's constraints (maxLength 32/120, minLength 3), so an agent could still trip validation.

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

Purpose3/5

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

"AI Agent Offer: one offer for the people ChatGPT, Claude and Perplexity send" names the resource but never states a verb for the read mode — the agent must infer from "With nothing: ...by engine with their conversions" that the default call returns a report. The dual read/write nature is discoverable, but the purpose is buried in a long clause rather than stated up front.

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

Usage Guidelines3/5

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

"With nothing" versus "With save" does give an implicit mode-selection rule, which is genuinely useful for a tool whose behavior flips on an optional parameter. However, there is no guidance on when to prefer this over siblings such as offer_plan or followup_offer, nor any stated prerequisite for setting an offer.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources