jp_utils

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

With no annotations provided, the description carries the full burden and delivers meaningful behavioral disclosure: it specifies the Hepburn romanization standard with concrete traits (gojuon, digraphs, sokuon doubling, chouonpu vowel repeat), year-granularity of era conversion, and flags transition-year handling via the _ERA_TABLE note. The main weakness is deferring details to 'the conversion docstring' and an internal table note that the agent cannot reliably access.

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 compact and well-structured, front-loading the operation list and then giving each sub-operation a focused one-liner. It is dense enough that every clause earns its place, though the linguistic jargon (gojuon, sokuon, chouonpu) adds some cognitive load without definition.

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 three-in-one dispatcher with 6 parameters, no annotations, and 0% schema coverage, the description covers an unusual amount: operation semantics, parameter value sets, conversion conventions, and output granularity. Remaining gaps are the unresolved docstring/_ERA_TABLE deferrals and no statement about invalid-input behavior (e.g., empty text or out-of-range years). An output schema exists, so return-value documentation is not required.

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 0%, so the description must compensate — and it largely does: text, target (with romaji|hiragana|katakana values), era (meiji|taisho|showa|heisei|reiwa), era_year, and year are all given meaning and accepted value sets. The one gap is the required 'operation' parameter, whose binding to the three named operations is only implied by the top-line 'kana_convert | era_to_year | year_to_era' list rather than stated explicitly.

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 clear subject ('Japan-locale utilities') and enumerates three concrete operations — kana_convert, era_to_year, year_to_era — each with its own verb-and-resource semantics (convert kana text, convert era to western year, convert western year to era). It is clear and specific, but it never references sibling tools to differentiate itself, so the 'distinguishes from siblings' bar for a 5 is not fully met.

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 through the sub-operation breakdown: the description tells you which parameters belong to which operation and what each operation computes. However, there is no explicit when-to-use versus when-not-to guidance, no mention of alternatives among the sibling tools (jlpt, kanji, vocab, etc.), and no exclusions or prerequisites. The routing is left for the agent to infer from the operation list.

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