Create an ACE referral from a short-lived server-side decision_ref returned by ACE Check. Caller-supplied Verdicts are never accepted as commercial eligibility proof.
| Name | Required | Description | Default |
|---|---|---|---|
| event_id | No | ||
| decision_ref | Yes | ||
| record_click | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations available, the description carries the full burden of behavioral disclosure. It reveals a nontrivial trust and safety trait: caller-supplied verdicts will never be accepted as eligibility proof, and the decision_ref is short-lived and server-side. It does not cover expiry/failure behavior, idempotency, or authorization, but it provides meaningful behavioral context beyond the action itself.
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 two sentences with no redundancy or filler. The main action is front-loaded, and the second sentence adds a crucial policy constraint that 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?
The core invocation is covered: the required parameter and how to obtain it are clear. However, the optional parameters are unexplained, no output or result shape is mentioned, and with no output schema or annotations an agent is left to infer post-creation behavior and failure semantics. It is sufficient for a straightforward call but not fully complete.
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 schema has 0% parameter description coverage, so the description must compensate. It does explain the required decision_ref parameter well, noting its source and short-lived nature, but event_id and record_click receive no semantic guidance. Coverage is therefore partial, and the optional parameters remain underspecified.
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 and object ('Create an ACE referral') and precisely scopes the input to 'a short-lived server-side decision_ref returned by ACE Check'. It also explicitly distinguishes itself from tools that might accept caller-supplied verdicts, making its purpose unambiguous.
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 clearly positions this tool as the follow-up to ACE Check: use it when you have a decision_ref from that call. The phrase 'Caller-supplied Verdicts are never accepted' functions as a when-not boundary, ruling out direct verdict input. It does not explicitly name alternatives, but the upstream relationship is clear.
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.
Most tools target distinct workflow stages (discovery, identity, claims, decision, referral), and the detailed descriptions help separate them. However, ace_check and commerce_preflight both expose ACE Verdict decisions, and verify_global_offer is an explicitly legacy alternative to commerce_preflight, so an agent can still misselect among the verification/decision tools.
All names are readable snake_case, and action tools use a verb_object pattern while query/metadata tools use noun phrases. The split is not chaotic, but it is inconsistent (e.g., product_discovery vs resolve_product_identity), and the commerce_/commercial_ prefix variation adds a minor wrinkle.
Fifteen tools is at the upper end of a well-scoped service and is reasonable for a broad commerce intelligence domain. The count feels slightly heavy because there are several descriptive/policy tools and at least one legacy overlap (verify_global_offer) that could be consolidated.
The set covers the core pre-purchase workflow: discovery, identity resolution, claim compilation, verification, recalls, merchant readiness, trust, referrals, and routing. Minor gaps exist, such as no explicit claim-management or decision-status retrieval separate from the decision products, but these do not create dead ends.