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

With no annotations, the description carries the full burden and does well: it discloses the required write:listings key, the key-owner identity restriction, the minimum-wage validation rule, and the fact that the first call returns a preview plus warnings rather than publishing. It stops short of saying what happens after publication (moderation, immediate visibility) or what errors look like.

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?

Purpose is front-loaded, then constraints, then a numbered two-step procedure — a well-ordered structure. The text is dense but nearly every clause carries operational information; only the minimum-wage figure and the '협의' rule could be argued as schema-adjacent detail.

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 13-parameter mutation tool with no annotations and no output schema, the description covers the critical unknowns: auth, validation floor, dry-run default, and the confirmation handshake. It is not fully complete because it omits sibling differentiation and any statement about what a successful publish returns or how failures surface.

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 62%, and the description compensates for the undocumented fields: it explains that wages are KRW integers, that hourly wage must meet 10,320 KRW, that wage_type='협의' is used for undisclosed pay, and it defines the dry_run/confirmed_by_user pairing as a safety protocol. The remaining required fields (employer_name, contact_phone, occupation) get no added meaning beyond their schema entries.

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?

States a specific verb and resource: registers an employer's Jeju job listing on jejusns.com. It is clear what the tool does, but it never distinguishes 'submit' from the sibling 'upsert_job_listing', so an agent must guess which one creates vs. updates.

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?

Gives an explicit two-step workflow with a hard prohibition ('do not call dry_run=false without user approval') and states the default dry_run=true behavior. The gap is that it never routes the agent away from upsert_job_listing or toward search_jobs for verification, so sibling selection is left implicit.

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