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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real behavioral context on top: leading-zero restoration, +82 conversion, extension preservation, and the failure mode "Unknown shapes return null." It does not clarify whether that null is per-element inside the returned array or for the whole call, which matters for a batch of up to 1000 inputs.

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?

Two sentences, both load-bearing: the first defines scope and output contract, the second lists the concrete transformations and the null failure behavior. The parenthetical coverage list is dense but front-loaded where an agent reading only the first clause still gets the core purpose.

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 two-parameter, non-destructive normalizer with no output schema, the description supplies scope, transformation rules, and failure behavior, which is nearly everything needed to call it correctly. The remaining gap is batch-level semantics (whether invalid entries yield nulls in place) and the 1000-item cap, which is left to the schema.

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%, with the style enum values and their formats spelled out inline, so the schema already carries parameter meaning. The description only adds that extensions survive normalization and that the result is "one style"; it does not explain the default style or how the style value interacts with the null fallback, so 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?

States a specific verb ("Normalize") and resource ("South Korean phone numbers") and then enumerates the exact number families covered (010, 02, 031-064, 070, 050x, 15xx/16xx/18xx). The output shape is also named ("to one style"), so an agent knows precisely what this tool produces without opening the schema.

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 makes the use case clear through the enumerated input families and normalization cases (Excel-dropped leading 0, +82 prefix, extensions), which tells an agent when this tool applies. It stops short of explicit when-not or exclusion guidance, and among the kr_* siblings none is named as an alternative for phone handling.

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