search_notes_in_report

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

No annotations exist, so the description carries the full burden, and it does well: it discloses the single-report scoping limit and that results carry no verdict/score/grade. It still omits error behavior, truncation/pagination, and rate limits, so it falls short of a full behavioral disclosure.

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 critical scoping warning and then the workflow, with per-parameter detail in a labeled Args block. It is long, but nearly every sentence adds operative information; the empirical aside ('8곳 → 15곳') is the only mildly expendable clause.

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 4-parameter, 0%-schema-coverage search tool with no annotations, the description supplies the scope, the workflow, every parameter's semantics, and the nature of the output (hit note number/title/excerpt, no scoring). Nothing an agent needs to invoke it correctly 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 0%, so the description must compensate, and it does for all four params: rcept_no format (14-digit DART number) plus how to obtain it per firm type, terms (whitespace-insensitive matching, the '|' OR operator, and that it is not a regex), mode's all/any semantics, and context_chars default of 600.

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+resource+scope: find note text by keyword within ONE disclosure report. It explicitly contrasts itself with a cross-company index search, so an agent can distinguish it from the many sibling discovery tools without opening the schema.

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 explicit when-not ('전 상장사에서 이런 주석이 있는 회사를 찾아줘'는 안 된다) and the required ordering (select a company first, then call with its rcept_no). It names concrete alternative entry points — get_unlisted_financials for unlisted firms and list_disclosures_by_stock for listed ones.

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