Search disclosure data fields

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavior beyond annotations: 'Turkish-insensitive' (a search behavior) and 'return path/value pairs' (output format). It also implies efficiency ('without reading the whole body'). No contradiction with annotations.

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 description is two sentences with no fluff. The core function is stated first, followed by a concise usage directive. It is front-loaded with the most important information and each sentence contributes value.

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?

Given that an output schema exists (per context signals) and annotations cover safety and idempotency, the description is largely sufficient. It clarifies the purpose, use case, and a key behavioral trait (Turkish-insensitivity). The only missing detail is behavior regarding 'sub_report_list' and what defines a 'match' (exact vs fuzzy), but these are minor gaps for a search tool. Overall, an agent can confidently call this 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 only 25% (only 'query' has a description). The description implicitly covers disclosure_id ('disclosure's structured data'), and the schema's query description gives examples. However, the description does not explain the 'limit' or 'sub_report_list' parameters, which are not described in the schema. Given low schema coverage, the description should compensate more, but for a search tool the parameters are fairly self-explanatory (limit is a count, sub_report_list likely filters sub-reports). Baseline 3 is appropriate.

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 a specific verb ('Find'), resource ('matching fields inside a disclosure's structured data'), and specifies the domain (financial statement line items, form fields). It also notes the return type ('path/value pairs') and a key feature ('Turkish-insensitive'). This distinguishes it from sibling tools like search_documents (which likely searches full text across documents) and get_financials (which may return entire financial statements).

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 description explicitly tells agents when to use it: 'Use to pull single figures from an official KAP financial report or form without reading the whole body.' This implies it is preferred over get_document_text when a specific figure is needed. It does not explicitly name alternatives or exclusions, but the use case is clear enough for an agent to select it.

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