GYEOL Site Maker

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

With no annotations, the description carries the full burden and does so well: it discloses latency (30–90 seconds), a concrete rate limit (max 3 per hour per caller), the cost model (free, no card), and the fact that the draft is unclaimed until the owner signs in. It also flags what the output will leave unresolved (photos, prices), which sets correct expectations about partial results.

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?

Three sentences, front-loaded with the action and its qualifiers, then latency and rate limit, then the return contract. Nearly every clause carries information an agent needs — cost, timing, throttling, and next-step URLs — with no padding.

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?

There is no output schema, so the description must describe the return payload — and it enumerates previewUrl, claimUrl, pages, and outstanding owner tasks. Combined with the latency and rate-limit disclosures, an agent has everything needed to call this correctly and explain the result to a user.

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% and each parameter already carries a descriptive string, so the schema does the heavy lifting. The description adds only the optionality framing ('url and/or a short description') and the return-value names; it adds no syntax, format, or constraint detail beyond the schema.

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 artifact — 'Create a free AI website draft' — with its defining attributes (Korean + English, multi-page, mobile-first) and its input sources (site URL and/or short description). That is clearly distinct from the sibling read-only tools gyeol_read_site and gyeol_pricing, so an agent can route without opening the 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?

It implies the trigger conditions ('from an existing site URL and/or a short description') and gives useful downstream instructions ('open it' for previewUrl, sign in at claimUrl to own the draft). But it never names an alternative or states when NOT to use it versus gyeol_read_site, so the routing decision is left implicit.

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?

With no annotations, the description carries the full burden and does well: it discloses currency (KRW), that VAT is excluded, the plan structure, and the free allowance of 3 AI drafts. It does not say whether prices are current or how often they change, but for a static informational lookup this is solid disclosure.

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?

One sentence, front-loaded with the resource, then plan types, then currency/VAT caveats, then the free tier. Every clause carries information; minor density from stacked parentheticals but no wasted sentences.

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?

There is no output schema, so the description must convey what comes back, and it does: build plans, monthly care plans, currency, VAT treatment, and free-draft allowance. For a zero-param informational tool this is nearly everything an agent needs to decide to call it and trust the result.

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?

Zero parameters, so baseline 4 applies. The description adds no parameter information because there is none to add, which is appropriate.

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 names a specific resource (GYEOL pricing for a small-business website) and enumerates the content buckets: one-time build plans, monthly care plans covering hosting/inquiries/AI edits, and the free tier. That clearly distinguishes it from the sibling tools gyeol_make_draft and gyeol_read_site, which act on drafts and sites rather than explaining pricing.

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?

Usage is implied – an agent answering a pricing or free-tier question would pick this – but nothing states when to call it versus gyeol_make_draft or gyeol_read_site, nor any exclusions. It reads as a catalog entry rather than a routing instruction.

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?

No annotations exist, so the description carries the full behavioral burden. It does disclose the read scope and one hard limitation (Instagram/Naver Place URLs fail), but says nothing about network failure modes, timeouts, permission/auth needs, or how long a fetch takes — meaningful omissions for a tool that scrapes a live external site.

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 sentences, no filler. The extracted-field list is front-loaded so the agent knows the value proposition immediately, and the ordering constraint follows.

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?

There is no output schema, so the description correctly enumerates the returned fields and notes the migration hand-off context. What's missing is failure behavior — what the agent sees when the site is unreachable or partially parseable.

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 a single required parameter at 100% schema coverage, the schema already defines the `url` field. The description still adds real constraints the schema does not: the URL must point at an existing business site with home/menu structure, and Instagram/Naver Place links are rejected.

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 (Read) + resource (existing business website, home + menu pages) and enumerates what comes back: title, pages, phone/address/hours, brand colors & fonts, photo count. This is clearly distinguishable from gyeol_make_draft, which acts on the information rather than extracting it.

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?

"Use before gyeol_make_draft to show the user what will be migrated" gives an explicit sequencing rule against a named sibling, and "Instagram/Naver Place links are not readable" rules out an input class. The only gap is that no alternative is suggested for those unsupported sources, so the agent knows what not to try but not what to do instead.

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