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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond those annotations: the hard session prerequisite and the conditional dependency between date_type and the other parameters. It does not contradict the annotations in any way.

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?

One dense paragraph front-loaded with the critical precondition ('REQUIRES...') before the purpose. The numbered date modes are easy to scan. It is slightly packed — the parameter requirements are crammed into parentheticals — but no sentence is wasted and the essential info is immediate.

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 10-parameter tool with no output schema, the description covers the three key agent-facing needs: the login prerequisite, how to pick a date mode, and the search_type semantics. It handles the conditional-parameter complexity well. Minor gaps: enum defaults (date_type='01', search_type='01') are only implied, and return values are unspecified, but the schema carries most of the remaining burden.

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 schema individually documents all 10 parameters, setting a baseline of 3. The description earns its keep by explaining the cross-parameter combinatorics that the flat schema cannot express — that date_type='01' REQUIRES start_date+end_date, '02' REQUIRES year+month, and '03' REQUIRES year+quarter, plus the issued/received mapping of search_type. This relational meaning is above baseline value.

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+resource ('Search e-tax invoice summary (totals)') and the title '전자세금계산서 합계 조회' reinforces the aggregation purpose. It is clearly a read-only summary search. However, it does not explicitly distinguish itself from the near-sibling hometax__etax__invoice__search_statistics, which sounds functionally similar, so an agent could hesitate between the two.

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 is rich in usage context: it mandates a prior login ('REQUIRES prior hometax__session__login call with same account_link_id') and precisely prescribes the three mutually exclusive date modes with their required parameter combinations. It does not, however, state when NOT to use this tool or name alternative tools (e.g., search_list vs search_summary), so the exclusion dimension is absent.

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