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

Beyond readOnlyHint=true, the description discloses the outlier exclusion rules (multiples <= 0, ROE > 100%), the units convention (decimals, 0.1 = 10%), how dividend yield is computed (forecast vs. actual), the share-class/market universe exclusions, the absence of a market-cap floor, and even the token cost. These are exactly the behavioral traits annotations cannot convey.

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 most important information (what it returns, what it's for) is front-loaded in the first two sentences, followed by caveats. The bilingual Japanese restatement is redundant for most readers but compact, and no sentence is filler.

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 no output schema, the description carries the burden of describing return content and does so by enumerating every metric and the all-market row. Units, exclusions and cost are covered; only the exact row/response structure is left unspecified, which is a minor gap for a small two-parameter read tool.

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 both parameters are already documented, including the tokyoPro enum value and the 4-digit sector code pattern. The description's restatement of the tokyoPro behavior largely duplicates the schema, though the 'no market-cap floor' and preferred-share exclusions add useful framing for what the filters actually select.

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 states precisely what the tool returns: median and quartile (Q1/Q3) values for PER, PBR, PSR, EV/EBITDA, ROE, ROA, dividend yield, market cap and 3-year growth, for each of the 33 TSE sectors plus an all-market row. That is a concrete resource with a clear shape. It does not explicitly name which siblings it replaces (e.g. get_sector_performance, get_peers), so an agent must infer the boundary itself.

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?

'Use it to judge whether a stock is cheap or expensive versus its industry' gives a concrete decision context for when to call it. There is no explicit when-not guidance or named alternative for single-company peer comparison, so the exclusion side is left implicit.

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