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

With no annotations, the description carries the full burden and does reasonably well: it discloses coverage (1,889 municipalities, 政令市 split by ward), the exact vintage and source of each metric (住民基本台帳 2026-01-01, 経済センサス 令和3年, 社人研 2050), and the fallback behavior of returning candidates when names collide. It does not state read-only/side-effect profile or any rate/limit behavior, though 'get_town' makes read-only self-evident.

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?

There is no filler — every clause names a returned metric — but it is delivered as a single dense run-on sentence with an embedded colon list, which is hard to scan. Splitting the metric list into a structured enumeration would make it materially easier to parse at similar length.

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 describe return values, and it does so thoroughly, including provenance and the ambiguity case. For a two-param lookup tool this is close to sufficient; the gaps are the missing not-found behavior and the unexplained relationship to get_industry / about_data.

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% and both parameters already carry descriptions including the name-or-code format and the disambiguation purpose of prefecture. The prose adds nothing about parameter format or behavior beyond the schema — the duplicate-name candidate behavior is the only extra, and it is arguably return-value semantics rather than input semantics. Baseline 3 applies.

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 enumerates exactly what is returned for a Japanese municipality: population (住民基本台帳 2026-01-01), 5-year change, 65+ share, 2050 IPSS projection, and industry-class counts plus two comparative category signals. That is highly specific to the resource. However, the framing verb 「数を返す」('returns the number of') is misleading for what is actually a multi-field profile lookup, and there is no differentiation from the sibling get_industry despite overlapping industry-category content.

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 rather than stated: the query param accepts a name or 5-digit code and prefecture disambiguates, and 「名前が同じ町が複数あれば候補を返す」 tells the agent what happens on ambiguity. But there is no explicit when-to-use versus about_data or get_industry, and no guidance on what to do when candidates come back.

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