SchoolOrder Catalog

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

No annotations are provided, so the description carries the full burden. '본다' implies a read-only retrieval and '전부' signals a complete listing rather than a paginated subset, which is useful. However, it says nothing about permissions, error behavior for an unknown slug, or response shape.

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 short sentences, front-loaded with what the tool returns, followed by the input provenance and the downstream use of the output. Every sentence earns its place with zero filler.

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 one-parameter read tool with no annotations and no output schema, the description covers the essential chain: source of input, what is returned, and how the output is consumed downstream. Only minor operational details (invalid slug handling, auth) are absent.

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% for the single slug parameter, so the baseline would be 3. The description adds real value beyond the schema by documenting where the slug comes from (search_school_saas), turning a bare identifier into an actionable dependency.

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: it returns all price options broken out by period and account count for a single product. It also distinguishes itself from siblings by naming search_school_saas as the slug source and quote_school_saas as the consumer of option_id.

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 gives clear context for use: pass in the slug obtained from search_school_saas, then feed each option_id into quote_school_saas. It does not explicitly state when NOT to use this tool versus list_school_saas_providers or school_purchase_guides, but the workflow positioning is unambiguous.

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 it does disclose the return shape (vendors plus per-vendor product counts) and, via '본다', that this is a read/browse operation. It says nothing about permissions, pagination, ordering, or result size limits, which are the remaining traits an agent would want for a listing tool.

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, and the what-it-returns statement is front-loaded ahead of the when-to-use statement. It is appropriately sized for a zero-parameter listing tool, though the second sentence repeats the browsing idea already implied by the first.

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 no-param, no-annotation, no-output-schema read tool, the description covers both the result content (vendors + product counts) and the selection context, which is essentially everything an agent needs to invoke it. The absence of ordering or scope limits on the list is a minor gap.

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 of 4 applies; there is no parameter meaning for the description to add or omit. The description's mention of 'current' vendors is the only input-adjacent nuance and it maps to an implicit server-side filter rather than a parameter.

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 verb+resource ('공급하는 제공사(벤더) 목록') and adds the payload detail that each entry carries a product count, so the agent knows exactly what comes back. It does not explicitly distinguish itself from siblings like search_school_saas or get_school_saas_product, which keeps it out of 5 territory.

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 states a use context — scanning which vendors' products could be adopted by schools — which implies a browse/overview moment rather than a targeted lookup. However, it names no alternatives and gives no exclusion criteria (e.g., 'use search_school_saas to filter by name'), so routing between the four siblings is left to inference.

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 must carry the behavioral load. It usefully discloses that volume-tier discounts are applied automatically and that the output is a link intended for school approval, but says nothing about whether the quote is persisted, whether it expires, required permissions, or repeat-call behavior.

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 short sentences, front-loaded with the core action (total + quote link) before the discount behavior and the dependency hint. No filler or restated field names.

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 three-parameter tool with no output schema, the description covers the essential outcome (a shareable quote link) and the pricing behavior. It is slightly thin on authorization and persistence details, which an agent pricing an approval workflow might want.

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 already 100%, so the baseline is 3. The description adds genuine meaning on top: it names the upstream source for option_id and links quantity to the automatic tier-discount logic, both of which the schema alone does not convey.

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 two concrete outcomes: computing a total from options and quantity, and producing an approval-ready quote link. This is clearly distinct from siblings like get_school_saas_product (a lookup) and search_school_saas (discovery), so an agent can route correctly 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?

Gives an explicit prerequisite: option_id must come from get_school_saas_product, which tells the agent what to call first. It stops short of stating when NOT to use this tool (e.g., for exploratory pricing) or how it differs from list_school_saas_providers, so it is strong but not exhaustive.

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 are provided, so the description carries the full disclosure burden. It does describe the two-mode read behavior (no slug = list, slug = body) and the content scope, which is useful, but it says nothing about freshness, permissions, or whether the guide content is static or fetched live.

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?

Four short sentences, front-loaded with the purpose and content scope before the invocation modes and the usage caveat. No filler, though the topic enumeration and the mode explanation slightly overlap in what they convey.

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 only two optional parameters, the description covers what the tool returns (a list or a guide body) and when to reach for it. It is adequate for the tool's complexity, with only minor gaps around content freshness and retrieval behavior.

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 description coverage is 100%, so both parameters are already documented. The description restates the slug/query semantics ('slug 없이 부르면 목록, slug 를 주면 본문') without adding format, syntax, or matching-behavior 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 (reads) and resource (procedural purchase guides for AI subscriptions), then enumerates the covered topics: S2B flow, budgeting, approval/quotation documents, tax invoices, account issuance. It also distinguishes itself from value-oriented siblings with 「값이 아니라 「어떻게 사나」를 물을 때 쓴다」, so an agent can separate it from get_school_saas_product or quote_school_saas.

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 a clear usage condition — use it for 'how to buy' questions rather than price/value questions — and explains the two invocation modes (list vs. body). It does not name any sibling tool explicitly, so the routing signal is contextual rather than a direct 'use X instead' 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?

With no annotations, the description carries the burden and does disclose the returned fields (name, slug, lowest price) and that richer price/period data lives in a sibling tool, which prevents an agent from expecting full pricing here. It stops short of covering auth needs, rate limits, or result-size behavior beyond the schema's limit default.

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?

Five short sentences, front-loaded with purpose then progressively detailing the handoff, query-less mode, and s2b filter. Dense but every clause adds routing or parameter information; not padded.

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?

No output schema exists, and the description compensates by naming the return fields and delegating price detail to the sibling tool. Combined with the fully documented schema and clear usage routing, an agent has everything needed to call this correctly.

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 already 100%, so baseline is 3. The description adds genuine meaning: query accepts brand names or Korean free text, category can be used alone, and s2b_only means 'purchasable on 학교장터' — semantics beyond the terse schema strings.

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 ('finds AI/edutech subscription products purchasable by schools/institutions') with scope and coverage of multiple vendors named explicitly. An agent can distinguish this search tool from get_school_saas_product and the other siblings without opening any 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?

Explicitly routes the agent: use get_school_saas_product for pricing/period options, omit query and pass only category when the brand is unknown, and enable s2b_only to restrict to School Marketplace listings. Both when-to-use and the alternative tool are named.

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