Deterministically recommends an offer based on goal, delivery mode, or price without inventing fit.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | Executive or company goal | |
| outcome_tag | No | Outcome tag keyword | |
| audience_tag | No | Audience tag keyword | |
| delivery_mode | No | Delivery format | |
| max_price_cents | No | Maximum budget in cents |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral insights beyond the readOnlyHint annotation: 'deterministically' and 'without inventing fit' tell the agent that the tool will not fabricate a match and may return no offer if no fit exists. This is useful context not captured by 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?
The description is a single, tightly worded sentence that front-loads the core action and key constraints. Every phrase contributes meaning without redundancy.
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 should explain what the return value looks like (e.g., an offer object or null) but does not. It also omits how parameters interact when multiple are provided. Given the tool's complexity and five optional parameters, this leaves significant 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?
Schema description coverage is 100%, so the baseline is 3. The description mentions goal, delivery mode, and price, but does not clarify how multiple parameters combine or prioritize each other. It adds minimal semantics 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 verb and resource: 'recommends an offer.' It also specifies the basis (goal, delivery mode, or price) and distinguishes itself from sibling tools like list_offers by emphasizing deterministic, non-fabricated recommendations.
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?
No guidance is provided on when to use this tool versus alternatives such as get_offer or list_offers. The description only explains what the tool does, leaving the agent to infer appropriate use cases from the sibling tool names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are mostly distinct: get_offer vs list_offers vs recommend_offer target different granularities, and get_public_proof vs search_public_proof follow the same pattern. The only potential confusion is between create_checkout_link and prepare_purchase_intent, but their descriptions clarify different purchase mechanisms.
All tools follow a consistent verb_noun pattern in snake_case (e.g., list_offers, create_checkout_link, search_faqs). No mixing of conventions or vague verbs.
10 tools is well within the ideal 3-15 range for a platform focused on offers, events, FAQs, proofs, and purchases. Each tool serves a clear purpose, and the count feels neither sparse nor bloated.
The tool surface covers offer discovery, retrieval, recommendation, purchase initiation, events, FAQs, proofs, and system capabilities. Minor gaps exist (e.g., no get_event or get_faq), but core workflows are fully supported for an agent-facing public server.