Poll the brand attestation request status for a droplinked shop. Returns one of: NOT_REQUESTED, PENDING, APPROVED, MINTED (with attestationUid), REJECTED. Use this to surface progress to merchants after they submit a request.
| Name | Required | Description | Default |
|---|---|---|---|
| shopSlug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description expands on the annotations (readOnlyHint, idempotentHint) by detailing the specific statuses returned and noting that MINTED includes attestationUid, which is beyond what structured data provides. It does not contradict annotations and adds useful behavioral context about the polling nature of the operation.
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 exactly two sentences, front-loaded with the core action and return values. Every sentence serves a purpose: the first states what the tool does, the second lists outputs and when to use it. There is no wasted wording.
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?
For a simple single-parameter polling tool, the description is thorough. It covers the action, the possible return values, and the intended use case. Since no output schema is provided, the description's enumeration of statuses and the attestationUid detail fully cover return value expectations. The annotations handle safety and idempotency, so no further context is needed.
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 description does not directly explain the shopSlug parameter, and schema description coverage is 0%. However, the single parameter is self-explanatory from its name and schema constraints (pattern, min/max), and the description references 'droplinked shop,' which aligns with the parameter. The schema's strong constraints compensate somewhat, but the description could have explicitly linked shopSlug to the shop context.
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 the specific verb 'Poll' with the resource 'brand attestation request status for a droplinked shop,' clearly distinguishing it from sibling tools like request_brand_attestation and verify_brand_attestation by focusing on status retrieval. It also lists the exact possible return states, leaving no ambiguity about what the tool does.
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 provides explicit usage context: 'Use this to surface progress to merchants after they submit a request.' This clearly indicates when to use the tool, but it does not explicitly name alternatives or state when not to use it. However, the context is sufficient to guide an agent's decision among siblings.
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.
Many tools have overlapping purposes, such as find_inventory, search_products, list_shop_products, and get_product all dealing with product discovery/retrieval with subtle differences. Similarly, verify_brand_attestation and get_brand_attestation_status could be confused, as could get_trust_dossier and get_underwriting_signals. The sheer number of verification and lookup tools makes it difficult to pick the right one without careful reading.
The cart tools use a dot-separated camelCase convention (cart.addLine, cart.updateLineQuantity), while the rest use snake_case with varied verbs (find_, get_, list_, search_, verify_, request_, quote_, etc.). This mixing of conventions and inconsistent verb choices (e.g., find_inventory vs search_products vs list_shop_products) makes the tool names unpredictable.
With 38 tools, this server is heavily overloaded. The guidance suggests 25+ tools is too many, and this server exceeds that threshold. While the domain spans commerce, trust attestations, and lending, the count is excessive for a coherent single-server toolkit.
The tool surface is extremely broad, covering cart management, checkout, product discovery, trust verification, and lending workflows. However, there are notable gaps: no cart retrieval or order history, no revoke/update for attestations, and some key lending tools (quote_credit_terms, report_repayment) are scaffolded but not yet functional, creating dead ends.
