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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds the 'Diagnostics-tier tool' label and explains the input requirement (known-correct version), which provides context beyond annotations. It does not fully describe output behavior or error cases, but the annotation coverage lowers the burden.

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 three sentences, front-loaded with the core purpose, and every sentence adds value: the first explains what it does, the second gives usage guidance and a sibling alternative, and the third sets expectations via 'Diagnostics-tier tool.' No filler or redundancy.

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?

With no output schema, the description does disclose the expected output categories (rule violations, boundary violations, systemic structural error, per-field contributions). It also provides usage context and a diagnostic tier label. While it doesn't detail the exact output shape or all edge cases, the combination of annotations and schema makes it sufficiently complete for a diagnostic tool.

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 parameters are already well-documented in the schema. The description references 'original and corrected values' and 'per-field contributions' but adds no new semantic detail beyond what the schema's property descriptions already provide. Baseline 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?

The description opens with a specific verb ('Split') and clearly states the resource and action: decomposing errors between original and corrected values into distinct categories (direct rule violations, boundary violations, systemic structural error). It also differentiates itself from the sibling tool analyze_anomaly, making the purpose unmistakable.

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 explicitly states when to use this tool ('Use with a known-correct version to diff against') and names the alternative tool for a different scenario ('use analyze_anomaly when you only have the suspicious payload'). This is an ideal when-to-use/alternative formulation.

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