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

Annotations only declare readOnlyHint; the description goes well beyond by disclosing the TOC shape (tag, Japanese heading, size), that MD&A sections can be very long, that image-embedded content is lost and rendered as "[画像]", and that a missing section produces a 404 whose body lists suggestedTags. These are the operational facts an agent needs to recover from failure.

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 correct call sequence, but the entire English text is duplicated verbatim in Japanese, roughly doubling length without adding information. The trailing ISO 8601 date-time note is generic boilerplate with little relevance to a narrative-text tool.

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 return-format burden and does so by describing the TOC fields and the plain-text conversion (tags stripped, tab-separated cells, "[画像]" placeholders). It is silent on how very long sections are bounded (truncation or pagination), which is the one remaining 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; the description earns more by enumerating the full alias vocabulary (business, risks, mdna, governance, rnd, facilities, etc.) that the schema only samples, and by explaining that `risks` always resolves to jpcrp_cor:BusinessRisksTextBlock. `fiscalPeriod` and `content` are only covered by the schema, not expanded here.

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 — narrative sections of the annual securities report (有価証券報告書) — and the two-mode retrieval pattern (TOC vs. section body). This is clearly distinct from the numeric XBRL/statement siblings such as get_balance_sheet or get_xbrl_facts.

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?

Gives an explicit two-step procedure: call without `tag` to get the table of contents, then call again with a tag/alias. It also names the correct alias for special cases (investment-risks for REITs/funds, going-concern-risks semantics varying by filer) and the fallback when `risks` is absent (404 with suggestedTags).

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