get_kernelSPARKS completeness tier for a brand in a market: 100 = resolvable (a real pack/size record is held) . 8 = registered (brand known, pack/size pending) . 'floor' = STANDARD default (no brand-specific record). Returns the stored tier flag — do NOT compute a score. Never returns a pack/size.
| Name | Required | Description | Default |
|---|---|---|---|
| node | Yes | ||
| brand | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden and does so well: it explains the stored-flag semantics, the meaning of each tier value, and the negative guarantee about pack/size. It also clarifies that the tool is a pure retrieval operation, not a computation. It does not discuss error behavior, but for a simple getter this is a solid disclosure.
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 compact and front-loaded with the core purpose, followed by useful value semantics and usage constraints. Each sentence adds information, and it avoids unnecessary filler. Minor formatting artifacts like the stray space before the period prevent a perfect score.
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 description covers the return values, the default behavior, and what the tool does not return, which is strong given that an output schema exists. However, it leaves the meaning of the 'node' parameter somewhat implicit and does not clarify how this tool relates to sibling tools like resolve_sparks. For a low-complexity two-parameter getter, this is adequate 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?
Schema description coverage is 0%, so the description must compensate. It indirectly maps the two parameters by saying 'brand in a market,' suggesting brand maps to 'brand' and node maps to the market context. However, it never explicitly names 'node' or defines what a node is, leaving some ambiguity for a tool with no schema-level parameter descriptions.
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 identifies the tool as returning a SPARKS completeness tier for a brand in a market and explains the three possible values (100, 8, 'floor'). It does not just restate the name 'get_kernel' and gives the agent a concrete sense of what the tool returns. It does not explicitly differentiate from sibling tools like resolve_sparks, which keeps it from a 5.
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 gives clear usage context: it returns the stored tier flag and explicitly warns not to compute a score. It also states that the tool never returns a pack/size, which helps an agent avoid misuse. However, it does not mention alternatives or give explicit when-to-use versus when-not-to-use guidance relative to sibling tools.
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.
Multiple tools overlap heavily: resolve_gtin, resolve_sparks, and get_signal_chain all resolve GTINs to different but closely related signals, and resolve_node vs node_market both return the same node with makers/retailers counts. Agents will struggle to pick the correct tool without reading deep into descriptions.
Most tools follow a clear verb_noun pattern (check_, count_, find_, get_, list_, resolve_), but node_market breaks the pattern and the get_ vs resolve_ distinction is not obvious. Overall readable with only minor deviations.
14 tools is well-scoped for a CPG knowledge graph covering GTIN resolution, eligibility, supply/demand search, node metadata, taxonomy, and brand coverage. Each tool reasonably earns its place without overwhelming the surface.
The surface covers the apparent domain comprehensively: GTIN resolution, eligibility checks, maker/retailer discovery, node/spine queries, SKU taxonomy, brand listings, signal chains, and registries. For a read-only knowledge graph, there are no obvious dead ends or missing core operations.