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

Annotations already carry the safety profile (readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds genuinely non-obvious behavior: results with unverified inventory are deliberately kept, availability=unknown means 'unknown,' not 'sold out,' and the agent is explicitly instructed to convey this to the user. This complements the openWorldHint and reveals a critical interpretation rule the agent would otherwise violate. 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 the purpose front-loaded first and the critical behavioral caveat set in bold immediately after. There is zero redundancy with the annotations or schema, and every sentence earns its place. It is efficient rather than sparse, though the purpose statement is minimal and could have elaborated on scope without harm.

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 (6 optional params, natural-language region matching with fallback semantics, inventory-dependent behavior) and the existence of a rich schema plus output schema, the description covers the essential non-obvious behavior: retention of unknown-inventory results and mandatory user communication. Return values are rightly delegated to the output schema. A minor gap is that the description does not mention that providing checkin triggers inventory lookup, though the schema covers 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 100%, so the baseline of 3 applies. The schema descriptions are exceptionally rich — region accepts abbreviated/formal names, falls back to substring matching, records the match type in meta.region_matched_on, and enforces that romanization works only at the province level. The tool description itself adds no parameter-level meaning beyond the schema, so no uplift is warranted.

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 (찾는다/finds), a well-defined resource (국내 숙소/domestic accommodations), and a filtering condition (조건에 맞는/matching conditions). This clearly distinguishes it from siblings: stay_booking_link, stay_detail, and report_issue are booking, detail, and issue-reporting operations, not search. The title '숙소 검색' is meaningfully expanded with '국내' and '조건에 맞는' rather than just restated.

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 implies when to use the tool (when the user needs accommodations matching conditions), and the sibling names make the alternatives obvious. However, there is no explicit routing such as 'use stay_detail for a specific property' or 'use stay_booking_link once a property is chosen.' No exclusion criteria or when-not-to-use guidance is given, leaving tool selection to inference.

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