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

Annotations declare openWorldHint=true, but the description says 'without browsing, enrichment, inference, or child calls' and promises 'stable groups', implying a closed, deterministic operation. This directly contradicts the openWorldHint annotation and creates significant uncertainty about the tool's actual behavior. ReadOnlyHint and destructiveHint are consistent, but the openWorldHint mismatch is a serious inconsistency.

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 plus pricing, with the action and grouping keys front-loaded in the first sentence. The second sentence lists output guarantees and exclusions concisely. There is no filler; every clause adds informative value.

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 a small 3-param schema with no output schema, the description covers input scope, output characteristics (stable groups, exact IDs, counts, SHA-256), and boundary conditions (no browsing, enrichment, inference, or child calls). It could mention error behavior or exact output format, but it is largely complete for a pure grouping tool. The openWorldHint contradiction slightly undermines overall completeness.

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 schema already documents all three parameters and their enums. The description adds a high-level enumeration of grouping modes and output digest details, but it does not provide field-level semantics beyond what the schema already explains, so the baseline score of 3 is appropriate.

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?

Description opens with the specific verb 'Split', identifies the resource ('bounded batch of normalized US brand signal rows'), and enumerates the grouping dimensions (brand, event type, severity, analysis status). The phrase 'without browsing, enrichment, inference, or child calls' helps distinguish it from sibling analysis tools, making its role 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 implies when to use the tool: when the agent needs deterministic grouping of already-normalized rows and explicitly wants to avoid enrichment, inference, browsing, or child calls. It does not name sibling alternatives explicitly, but the exclusion list provides clear when-not guidance, making usage context sufficiently clear.

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