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

Annotations already declare readOnlyHint=true, so safety is covered. The description does add genuine behavioral context beyond that: the row shape (element × context with labels, dimension members, numeric or text value), that ratios are decimals, and the important caveat that accountingStandard is the filing-level DEI declaration and can mislabel rows, so tag prefix is the real discriminator. It stops short of return ordering, pagination, or what happens when a symbol has no filing.

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 guidance is fully duplicated in Japanese, roughly doubling length with no new information for a single agent, and the trailing ISO 8601 date-format paragraph is largely irrelevant to a tool with no date parameters. The most decision-critical content, the tag-prefix vs accountingStandard caveat, is buried mid-paragraph inside a long run-on rather than front-loaded.

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 returns and does so adequately: it names the per-row fields (labels, dimension members, value) and clarifies numeric-vs-text and ratio encoding. For a 5-parameter filtered-list tool with one required parameter, that is nearly complete; only pagination/limit behavior and empty-result behavior are left implicit.

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 80%, so the baseline is 3, and the description earns above that by giving worked tag examples, explaining that tag matching is case-insensitive substring on the element name, listing all category values with their effect, and warning that a tag family (jppfs vs jpigp) is not the same as accountingStandard. It says nothing about `limit` or about `fiscalPeriod` beyond the schema's own 'omit for latest' wording.

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: "Raw XBRL facts from the annual securities report," and pins the row granularity as "one row per element × context," which is exactly the distinction an agent needs versus aggregated siblings like get_balance_sheet or get_income_statement. The category enum values are named inline, so the resource is unambiguous.

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 concrete narrowing instructions ("Narrow with `category` ... and `tag` ... e.g. \"Assets\"") plus disambiguation of lookalike tags (jppfs_cor_Assets vs jpigp_cor_AssetsIFRS, _bs suffix, TotalAssets meaning only the business-results summary). What it never says is when to pick this over get_balance_sheet or get_full_financial_statement, so the sibling routing is implied rather than explicit.

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