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

With no annotations, the description carries full responsibility for behavioral disclosure. It is exceptionally thorough: zero-padding to 14, branch-specific outcomes (full license record vs. gated proof), explicit note that pack/size VALUE is never returned, routing to Navigator, and fail-closed brand matching with uncertainty represented as recognized:false. No annotation contradiction exists since annotations are absent.

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, moderately dense block but is logically structured into two branches with a note on brand matching. It front-loads the core purpose ('Two-branch SPARKS resolver') and then elaborates. Every sentence contributes information; there is no fluff or redundancy. Slightly dense, but appropriate for the complexity of the two-branch logic.

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?

Given the tool has an output schema (context indicates has_output_schema=true), the description does not need to fully explain return shapes. It already specifies what Branch A returns (full license record) and what Branch B returns (gated proof with specific fields and exclusion of pack/size). It also covers failure semantics and routing. All necessary behavioral context is present, making it complete for an agent to invoke correctly.

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 input schema only defines a single required string 'gtin' with 0% description coverage. The description compensates by explaining that it is a GTIN that gets zero-padded to 14, and differentiates behavior based on the GTIN prefix (e.g., 990832300xxx). This adds meaningful semantic value beyond the bare schema, though it does not specify exact format constraints (like allowed characters) or give examples. Given the low schema coverage, the description does enough.

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 resolves SPARKS and distinguishes two branches (GSC versus third-party BPC GTINs). It specifies the resource (SPARKS) and the operation (resolver). It does not explicitly name a sibling tool to differentiate from, but the branch logic and the 'Route to Navigator' instruction make the purpose clear enough for an agent to select it correctly.

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 a clear trigger for when to use the tool: a GTIN that is either a GSC Territory/License GTIN (Branch A) or any third-party BPC GTIN (Branch B). It also notes fail-closed behavior and uncertainty handling. Although it doesn't explicitly list alternatives, the conditions effectively indicate which input types are appropriate, and the 'Route to Navigator' hint suggests a downstream action. Slight lack of explicit 'when not to use' guidance, but the branches define the scope well.

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