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

Annotations already declare readOnly=false and destructiveHint=true. The description adds useful behavioral nuance: this is a write operation and is reversible only while the draft is in 작성중 status. That is meaningful context beyond the structured annotations. No contradiction found.

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?

Two dense sentences with no filler. The prerequisite is front-loaded, the main action is clearly stated, and the reversibility caveat earns its place. Every sentence adds value.

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 mutating tool with 7 parameters and no output schema, the description covers the critical workflow: login prerequisite, target_search as ID source, draft context, and reversibility condition. The main gaps are explicit sequencing with target_init/submit and any expected response, so it is strong but not fully complete.

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?

With 100% schema description coverage, the baseline is 3. The description adds extra meaning by tying target_irnos to target_search results and by requiring account_link_id to match the prior login session. This goes beyond what the schema states.

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 operation: naming selected insured persons (피보험자) as subsidy targets on an existing draft, using irno values from target_search. This is a specific verb+resource description that distinguishes the tool from search/read siblings like target_search.

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 a hard prerequisite: prior work24__auth__npki_session__login with the same account_link_id. It also indicates the right upstream data source (target_search irno values). It does not explicitly name alternatives or when-not-to-use conditions, so it stops short of a 5.

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