WOOKANG TECH LED sign quote

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

Annotations already declare read-only, closed-world, idempotent behavior, and the description adds meaningful context beyond them: licenses are credentials rather than a delivery track record, and the A/S promise includes warranty years and response/visit hours. This helps an agent interpret the facts correctly and avoid overstating the company's reliability.

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 description is front-loaded with the core resource and uses a second sentence for usage guidance and a third for follow-up routing. It is efficient, though the long parenthetical enumeration in the first sentence makes it slightly dense.

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 zero-parameter, read-only tool with no output schema, the description is complete: it names the information categories returned, clarifies an important caveat about licenses, and specifies a follow-up action. An agent has enough context to know when and how to use it.

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?

The tool takes zero parameters, so the baseline is 4. There is no parameter syntax to explain, and the description appropriately focuses on returned information rather than input semantics.

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/resource ('Company facts for WOOKANG TECH') and enumerates the exact content areas: phone, address, hours, service area, licenses, A/S promise, and document links. This clearly distinguishes it from the sibling tools get_price_range and submit_inquiry.

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 explicit usage triggers: 'Use when the user asks who the company is, whether it is trustworthy, how to contact it, or about warranty.' It also routes to submit_inquiry for callbacks, but does not explicitly mention get_price_range as the alternative for pricing questions or state when not to use this tool.

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

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

Beyond readOnly/idempotent annotations, it discloses the money semantics (KRW, min–max, VAT included, installation extra), that output matches the official wooktech.co.kr calculator, and the important edge case where large sizes yield result="staff_quote" with no amount. That is exactly the behavioral context annotations cannot carry.

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 core capability, trigger and edge case are front-loaded in the first three sentences. The final Korean sentence largely restates the English trigger and next-step guidance, so it is redundant rather than harmful; trimming it would make the definition tighter.

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 four-parameter read-only estimation tool with no output schema, the description supplies everything needed: what is priced, currency and tax treatment, the no-amount fallback, and the recommended next action after answering. Nothing an agent needs in order to call it and act on the result 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 width_m, height_m, place and what_where are already documented including units, ranges and the indoor default. The description adds only indirect hints (site examples like school gate/shop front that map loosely to what_where), so baseline 3 applies.

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 — estimate a KRW min–max price range for an LED display of a given size, supplied and installed by WOOKANG TECH — plus the pricing basis (VAT included, installation extra, matching the official calculator). This clearly separates it from get_company_info and submit_inquiry, which are informational and transactional rather than calculative.

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 trigger ('use this whenever the user asks how much an LED screen, 전광판 or 전자현수막 costs, or is planning one') with concrete site examples, and names the follow-on alternatives: submit_inquiry for a phone consultation (with consent prerequisite) or quote_url. It also states the negative case — when result is 'staff_quote', do not guess a number.

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

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

Adds real behavior beyond annotations: the asynchronous callback SLA (1 business day, weekdays), what the callback contains (feasibility + approximate price), and the server-side 400 rejection without consent. It does not describe rate limits or whether multiple submissions create duplicate tickets to the same number.

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 consent requirement is correctly front-loaded, but the entire description is effectively delivered twice (English then Korean), roughly doubling length without adding new information for an agent that already parsed the English. Size is defensible for a consent-gated write tool, but the duplication is not earning its place.

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?

With no output schema and full annotation coverage, the description still supplies everything an agent needs: the consent gate, the callback expectation, the failure mode, and which fields to fill for staff preparation. Nothing required to invoke 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 baseline is 3; the description goes further by explaining consent as an explicit privacy agreement (개인정보 수집·이용 동의) and by framing what_where and size/place as optional preparation aids 'if known'. Marginal gain over schema but meaningful for the consent gate.

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 ('Submit a phone-consultation / quote request to WOOKANG TECH') plus the outcome (staff callback within 1 business day with feasibility and approximate price). This clearly separates it from siblings get_company_info and get_price_range, which are read-only lookups.

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?

Explicit preconditions: call ONLY after the user explicitly agrees to phone-number use, ask for the number if missing, never use made-up/test numbers, and set consent=true. It also names the failure mode (400 rejection without consent), which is stronger than most when-to-use guidance.

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