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

With only readOnlyHint=true supplied, the description carries real behavioral weight: no-look-ahead disclosure timing, PER null on losses, yield as a decimal, J-REIT half-year annualization formula, null when the dividend does not span 12 months, transition-year handling, and a stated cost of 10 tokens. These are non-obvious semantics an agent could not infer from annotations or schema.

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 method is front-loaded and information-dense, but the entire body is then restated in Japanese, which is pure duplication for an agent reader, and there are drafting defects ('The the annual dividend'). Useful content, but the size could be cut substantially without loss.

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 5-parameter read-only tool with no output schema, the description covers computation method, null cases, window limits and timezone, and even names fields (eps, epsPeriod) that come back. Only the interval granularity (weekly/monthly last-trading-day behavior) and the overall shape of the returned series are left to the schema, a small residual gap.

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 the baseline is 3, but the description adds meaning beyond it: the 10-year maximum window, JST date semantics, and the concrete downstream consequences of basis=fy versus basis=ttm on which EPS/BPS period is used. It does not elaborate on interval, which the schema handles adequately.

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?

States a specific verb-and-resource pair: daily PER, PBR and dividend-yield series for a Japanese stock, including the exact computation inputs (split-adjusted close divided by EPS/BPS/DPS of the latest disclosed period). It also distinguishes itself from the point-in-time sibling by noting basis=ttm gives 'the same PBR as get_key_metrics_latest', so the agent can separate this history tool from the latest-snapshot tool.

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 context is clear — historical daily valuation series, default one year, max 10 years, dates in JST — and the basis choice is tied to a concrete alternative (screener's PER for fy, get_key_metrics_latest's PBR for ttm). It never explicitly says when NOT to use this tool or names the sibling to pick instead for a single current value, so it falls short of full alternative routing.

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