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

Annotations already declare readOnlyHint and openWorldHint=false, so the safety profile is covered; the description adds real behavioral context by stating it returns ranked candidates with confidence rather than a single match, which tells the agent to expect ambiguity handling. It stops short of describing no-match behavior, tie-breaking, or result count limits.

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 input surface and return behavior are front-loaded in a single dense sentence, with the Korean tagline as a minor search aid at the end. No filler, though the parenthetical digit counts duplicate the schema and could be trimmed.

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 zero required parameters, the most important missing piece is whether at least one identifier is mandatory and what happens if several are passed at once; the description only implies an 'or' relationship. Return values are sketched ('candidates with confidence') but there is no output schema to fall back on for the exact shape.

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 100%, so every parameter already carries its own Korean/English label, digit count, and hyphen tolerance. The description largely restates those digit counts (10, 13, 8) without adding precedence rules for when multiple identifiers are supplied, and it omits the stock-code option that the name parameter's schema documents.

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 ('Find the Jaryo entity for a Korean company') and scopes the input surface to names or official identifiers, which is far more precise than the bare name 'resolve_company'. It hints at resolution semantics ('Returns candidates with confidence') that differentiate it from search_companies, but it never names or contrasts the sibling tools explicitly.

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?

Usage is implied: you call this when you hold a company name, stock code, or one of four Korean identifiers and need the canonical Jaryo entity. There is no explicit when-not guidance, no statement about preferring get_company once an id is known, and no mention of how this relates to verify_company or search_companies. The agent must infer the routing from names alone.

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