list_financial_document_candidates

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

With no annotations, the description carries the full burden of behavioral disclosure, and it does so extensively. It reveals that the tool scans all submissions of a report (not just the exact rcept_no), that returned rcept_no may differ from input, that it does not return original text, and the performance implication of omitting corp_code (slower full-date scan). It also explains the default behavior of allow_body (hides body) and the confirmation requirement.

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 moderately sized but every sentence serves a purpose. It is well-structured: function overview, behavioral nuance, AI usage instruction, and parameter definitions. No fluff or redundancy, though it could be slightly tighter by merging some sentences. The front-loaded purpose helps immediate comprehension.

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 the tool's complexity (3 params, no output schema, no annotations), the description is exceptionally complete. It explains the return behavior (candidates with date, title, candidate_id), the pipeline integration with create_financial_workbook, the rcept_no discrepancy, and the performance trade-offs. An agent has all necessary information to call this tool correctly and decide whether to use it.

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 description coverage is 0%, so the description is the only source of parameter meaning. It thoroughly explains each parameter: rcept_no as a 14-digit receipt number to pass from search_disclosures, corp_code as an 8-digit code to pass if available (with a consequence for omission), and allow_body with its default false and the requirement for user confirmation before setting true. This far exceeds the bare schema.

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 clearly states the tool's function: '공시 계열(원본·정정·추가) 전체의 문서를 후보로 반환합니다' (returns documents of the entire disclosure series as candidates). It specifies the resource (disclosure documents) and the action (listing candidates), and distinguishes itself from get_disclosure_document by explicitly noting it does not return original text, only candidates with date/title and candidate_id.

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 gives explicit usage instructions: instructs the AI to select one candidate_id from the returned date/title and pass it verbatim to create_financial_workbook. It also specifies when to pass corp_code (if available from search_disclosures) and when to set allow_body to true (only after user confirmation). These are clear usage guidelines, though it doesn't name alternatives; the pipeline context makes the intended usage unambiguous.

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