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

With only sparse annotations (readOnlyHint=false, destructiveHint=false), the description carries the transparency burden and does substantial work: it discloses the fallback strategy and its 14% missing rate, the requirement for a platform service key (no account_link_id), the OPENDATA_ENABLED=1 server prerequisite, and the result-interpretation caveat. These go well beyond what the annotations provide. It loses a point only for not addressing pagination limits (hard max 20 pages implies possible missed rows) or rate-limit behavior.

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 four dense sentences with the purpose front-loaded and every clause earning its place — source, strategy, caveat, auth, config. It is admirably compact for the amount of operational detail it conveys, though the unexplained internal designations (M1, B-5, M1_WITH_FALLBACK) are cryptic jargon an agent cannot act on, which nudges it below a 5.

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 an 8-parameter tool with no output schema and minimal annotations, the description is thorough on behavior, auth, deployment requirements, and result interpretation. The notable gap is the return shape: no output schema exists, yet the description never indicates what fields each disclosure row contains, so an agent cannot tell whether the result will answer a specific question (e.g., whether administrative dispositions are included, as the title suggests).

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, but the description adds real parameter meaning: it explains that upstream truly requires sDate/eDate and that the required bizno is a post-hoc match key against ncrMasterNum rather than an upstream query field. It also quantifies the corp_name fallback scenario with missing_rate=0.14, which the schema does not. This is meaningful added semantics, not schema restatement.

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 opens with a specific verb+resource pair — 'Look up KISCON construction-firm disclosure rows' — and pinpoints the exact upstream endpoint (data.go.kr 15061362 ConAdminInfoSvc1/GongsiReg). This immediately distinguishes it from similar siblings like opendata__g2b__sanction and opendata__env__waste_sanction by naming the KISCON data source, so an agent can tell them apart 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?

The description gives clear operational context: the window-based matching approach, that upstream keys on sDate/eDate rather than bizno, and the corp_name fallback path. The caution that 'Empty matches mean no hit in this window — not a certified clean claim' is especially useful for when an agent should not treat a null result as a definitive negative. However, it never explicitly names sibling alternatives or states when to prefer g2b/env-sanction tools, so exclusions are absent.

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