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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral detail beyond those: outputs a stable/semantic grouping key, 'reports every token removed', and 'flags' obfuscation such as homoglyphs and invisible characters. No contradiction with annotations.

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?

Three sentences with no filler: the core transform, its deterministic nature, the report/flag output, and the relationship to sibling tools are all packed in efficiently. The most important behavior is front-loaded before the output details.

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 read-only, idempotent transform with two simple parameters, the description plus schema cover the essential calling intent. The main gaps are the unexplained `type` parameter and lack of explicit output shape, but the report/flag language gives enough expectation for an agent.

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 coverage is 50% because `type` lacks a description beyond its enum values. The description does not explain what `type` does (company vs. person) or how it affects legal-form splitting, nor does it compensate by describing parameter interaction. The only parameter gloss comes from the schema's one-line `name` description.

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 a specific verb and resource: 'Reduce a name to its comparable core with the legal form split out'. It also distinguishes itself from siblings by stating it exposes 'the normalisation the matching tools apply, on its own', making it clear this is the standalone transform versus match/compare/deduplicate tools.

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 clearly situates the tool as the normalisation layer beneath the matching tools, giving an agent context on where it fits. It implies use this when you need the grouping key or the removal/obfuscation report directly, though it does not explicitly list exclusions or name specific alternative conditions.

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