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

Annotations already declare readOnly/openWorld=false/idempotent, so the bar is lower, yet the description adds real behavioral context beyond them: prices exist only where a public consumer price is published (no member-tier pricing), stock is a three-state label snapshotted at response time rather than a quantity, and sale_unit differs from consumer_price.unit. Only pagination/result-cap behavior is left unaddressed.

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 and scope come first, then constraints, then the outbound pointer to 짓피티 — a sensible front-loaded order with no filler sentences. The category list at the start duplicates the enum already present in the schema, which is mild redundancy but aids scanning.

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 nine-parameter, all-optional search tool with an output schema, the description covers scope, filter-value sourcing, pricing and stock semantics, and answer-formatting conventions (짓닷코드 + 표시명 + urls.document). The notable gap is routing to check_stock when the caller needs current stock, given the description admits stock is only a response-time snapshot.

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 78%, so the baseline is 3, and the description mostly restates what the schema already says — the 'use only list_filters values' rule for material/finish is already in the material and category parameter descriptions. It adds the useful distinction between sale_unit and consumer_price.unit, but those are output fields, not request parameters.

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 and resource — finding interior materials published on jitdot.com — and enumerates the whole category scope (타일 · 마루 · 카펫타일 · LVT · 포보 · 욕실도기 · 벽재 · 부자재). It also points to list_filters as the value source and to 짓피티 for conversational search. It does not, however, differentiate itself from get_materials or check_stock, which an agent could easily confuse with a filtered lookup.

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?

There are concrete usage rules: size/material/finish values must come from list_filters, and bathroom fixtures/wall finishes/supplies should be searched by category plus keywords rather than by spec fields. It also routes recommendation-driven conversational lookups away to 짓피티. Missing is explicit guidance on when to prefer this over get_materials or check_stock.

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