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

With only readOnlyHint=true supplied, the description carries real weight and delivers: row ordering, the full metric list, the rule that outliers are null rather than omitted, the decimal convention for ratios (0.1 = 10%), how dividend yield is computed (forecast vs. actual annual dividend), and the explicit 10-token cost. That is substantive behavioral context an agent could not derive from the annotation.

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?

Front-loaded with the comparison purpose, then composition, then metric list and formatting caveats — a logical flow with no filler sentences. The Japanese restatement and the trailing cost note are reasonable for a bilingual tool, though the Japanese line adds no information the English sentence lacks.

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 the return shape — and it does, naming every column, defining null handling, ratio formatting, and the dividend-yield formula, plus row ordering. For a two-parameter, read-only lookup, nothing an agent needs in order to call and interpret it is missing.

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 schema already documents both symbol and limit, giving a baseline of 3. The description adds ordering knowledge that affects how row count should be interpreted (target row plus peer rows plus a median row), but it never states explicitly whether limit counts peers only or total rows, so the one genuinely ambiguous parameter remains ambiguous.

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?

"Compare a stock with its sector peers" is a precise verb+resource, and the description goes further by specifying the exact composition (target first, same-sector large caps closest in market cap, sector-median row) and the metric set returned. This distinguishes it clearly from siblings such as get_sector_performance or get_industry_benchmarks, which do not return a per-stock peer table.

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 comparative context is clear (same TSE 33 sector, similar market cap, common stocks only), which implicitly tells the agent this is a relative-valuation tool. However, no alternative is named and no exclusion stated — an agent must infer on its own when to prefer this over get_industry_benchmarks, get_key_metrics_latest, or get_sector_performance.

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