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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, yet the description adds genuinely new traits: no platform key exists, an external registration step is required before first use, upstream paging yields up to 100 records before winner/title filtering, and the 31-day window cap. These are the failure modes an agent would otherwise hit.

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 purpose and BYOK constraint are front-loaded, and the example is placed last, which is the right ordering. Some redundancy exists: the key-registration instructions repeat what the _apiKey schema property already says, costing a sentence or two.

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?

Covers auth acquisition, window limits, filter semantics, paging behavior, and return fields, with an output schema also present to handle response shape. For a 9-parameter external-data tool, nothing an agent needs in order to call it correctly is missing.

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; the description still adds value by grouping the filters conceptually (procurement type, date window, notice number, winner text, title text) and supplying a concrete worked example call. It does not add syntax detail beyond the schema, so not a 5.

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?

Names the specific resource (South Korean public-procurement AWARD results, 'who won which bid'), its source (Public Procurement Service successful-bid records), and its distinguishing scope (multi-year, not just the last 12 months). An agent can separate this from korea_search_tenders (tenders) and korea_get_vendor (vendor records) without opening a 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?

Gives clear operating conditions: BYOK is mandatory, the key must come from data.go.kr, and award windows are capped at 31 days per call. It also notes notice_no works 'instead of a date window.' It never explicitly states when to prefer korea_search_tenders or korea_search_vendors over this tool, so it stops short of 5.

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