2つの法人名が同一法人を指すか判定

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

With no annotations provided, the description carries the full burden and exeeds it. It discloses return structure (verdict, evidence, machine-generated reasons), constraints on 'likely_different' (only when common prefix/suffix and clearly different remaining elements), the rationale for returning 'unknown' in ambiguous cases, confidence cap at 'medium' due to 2006 company law, and type-level enforcement that confidence cannot contradict verdict. This is exhaustive and non-redundant.

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 long but highly dense and well-structured. It front-loads the core purpose in the first sentence, then systematically addresses response format, verdict rules, edge cases, confidence constraints, and verification caveats. Each sentence introduces a distinct behavioral rule with rationale, so nothing is redundant. However, its length slightly exceeds minimal conciseness, though appropriate for the tool's complexity.

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?

There is no output schema, so the description must explain return values; it does so comprehensively by specifying the three verdict values, the evidence structure, the machine-generated nature of reasons, and the confidence constraints. It also covers all critical edge cases and the legal background for confidence capping. Given the tool's complexity and lack of structured output metadata, this description is complete and self-sufficient.

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%—both parameters (nameA and nameB) have descriptions ('比較する法人名A/B'). The tool description does not add parameter-specific semantics (e.g., required format, examples) beyond the schema. Since the schema fully documents parameters, the baseline of 3 is appropriate; the description's behavioral details don't directly enhance parameter understanding.

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 clearly states the tool's function: it normalizes and compares two corporate names, then returns a likelihood of them referring to the same entity along with reasoning and confidence. It distinguishes itself from siblings like normalize_company_name (which normalizes a single name) and generate_matching_key (which creates keys) by focusing on pairwise comparison and verdict output.

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 provides strong contextual usage guidance without explicitly naming sibling tools. It explains edge cases where the tool returns 'unknown' (character-type mismatch, prefix/suffix position difference, entity type difference), which helps an agent decide when output is unreliable. It also states that '確実な同一性判定には法人番号での突合が必要です' (definite identity requires corporate number matching), implicitly steering users to other tools for definitive verification.

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