윤슬 Yunseul — 사주 만세력

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

No annotations are provided, so the description carries the full behavioral burden. It discloses cost ($0.1/call) and authentication (API key required), which are important, but does not state whether the operation is read-only, whether it stores data, or how errors (beyond the schema's 422 for unknown city) are handled. For a computation tool with zero annotations, this is adequate but incomplete.

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 two compact sentences plus a parenthetical, with the core purpose front-loaded and no wasted words. Every clause adds useful information (scope, relation options, cost/auth).

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?

Given the tool's complexity (astrological compatibility from two detailed birth charts) and the presence of an output schema, the description covers purpose, relation variants, and practical constraints. It omits edge-case behavior and explicit alternative routing, but is largely sufficient for an agent to invoke it 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 description coverage is 0% at the top level, so the description must compensate. It adds meaning for the relation parameter by listing four relationship types and noting that ten-gods/roles/cautions are added, but it does not explain the a and b birth-chart inputs beyond '두 명식'. The nested AgentBirth schema does document fields, but the top-level parameters remain largely undescribed in the description.

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 the specific analysis (궁합) and its scope: two birth charts' day stems/branches harmony-clash and five-element complementation. It distinguishes from single-chart siblings like saju_chart by specifying '두 명식' (two charts), but does not explicitly name any sibling tool for negative differentiation.

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?

The relation parameter options (연인|직장/동료|친구|사업 파트너) imply the tool is used for comparing two people in a specific relationship context, and the parenthetical notes prerequisites (paid $0.1/call, API key required). However, there is no explicit when-to-use versus alternatives or when-not-to-use guidance.

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 provided, the description carries the full disclosure burden, and it does communicate two important behavioral facts: the call is paid ($0.02 per invocation) and an API key is required. It does not state idempotency, error behavior, or the difference between the outputs of the sibling tools, but the pricing and authentication disclosures add real operational context that an agent should know before invoking the 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?

The description is one short sentence with a parenthetical, so it is not verbose. However, the paid-call and API-key note sits inside the explanation of what the tool computes, which slightly muddles the structure. Front-loading could be improved.

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?

The tool has an output schema, so return values need not be described. Still, with no annotations, minimal schema coverage, and five sibling tools in a similar domain, the description is incomplete: it fails to explain when this tool should be selected, what distinguishes it from saju_chart or monthly, and what the date parameter expects.

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 0% and the single required parameter is named only as 'date' with no format or timezone guidance. The description hints at the date's role in determining pillars and solar-term boundaries, but it does not compensate for the schema's omission. With only one parameter, though, there is limited ambiguity.

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 identifies a domain concept (the day pillar of a particular date, plus month/year pillars according to solar-term boundaries) but never states a clear verb+resource. It reads more like a label for an astrology calculation than a description of an operation that an agent can match against a sibling tool. The parenthetical notes about paid pricing and API-key requirements do not clarify the purpose.

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?

No when-to-use, when-not-to-use, or alternative-routing guidance is provided. The description does not differentiate this tool from siblings such as saju_chart, unse, or monthly, which appear to operate in the same domain. An agent has no basis from the description for choosing day_pillar over a sibling.

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 behavioral burden, and it does disclose that the tool is free and callable without an API key — genuinely useful auth/cost context. It says nothing about return shape, pagination, or rate limits, though the presence of an output schema covers return structure.

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 short fragments with no padding, and the cost/access constraint is stated immediately. Very terse, but every clause carries signal.

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, output-schema-backed listing tool, the description covers what the tool returns and the key caller-facing constraints (free, no key). Nothing critical for invocation 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?

The schema has zero parameters, so there is nothing to document; the baseline of 4 applies. The description correctly implies a no-argument listing call.

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 it returns per-tool pricing and descriptions, a clear resource scope. Since all siblings (compatibility, day_pillar, monthly, saju_chart, unse) are divination tools, this one is distinguishable as a metadata/pricing lookup, though it is phrased as a noun list rather than a verb+resource action.

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 only implied: an agent can infer it should call this to learn about pricing or tool descriptions before using the paid siblings. There is no explicit when-to-use/when-not statement or reference to alternatives.

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 behavioral burden, and it does contribute two useful facts: the call is paid at $0.1 per call and an API key is required. However, it says nothing about failure modes (e.g. what happens with a malformed period), rate limits, or whether the period must be the current month, leaving the safety profile thin.

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?

A single front-loaded clause names the tool's scope and its returned content, with a compact parenthetical for cost/auth. No filler, though the output enumeration is 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?

An output schema exists, so return values needn't be explained, and the description does outline the analytic content delivered. It remains incomplete on the two things an agent must decide on its own: how this differs from sibling fortune tools and what the period string must contain.

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?

Top-level schema description coverage is 0% and the two required params (birth, period) have no inline descriptions, so the description must compensate. It partially does so by signaling the period format as YYYY-MM, but says nothing about the birth object beyond what the nested $defs already document.

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 (이달의 세운, this month's fortune) and scopes it precisely to the solar month (양력 월, YYYY-MM) measured by solar-term boundaries, then enumerates the outputs (월주·십신·일지 관계·좋은 날·주의 날). This is far more specific than a name restatement, though it never explicitly contrasts itself with siblings like unse or day_pillar.

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 is no statement of when to choose this tool over unse, day_pillar, saju_chart, or compatibility. Usage is only implicit from the word 'this month', and no exclusions or prerequisites are stated beyond the pricing/auth note.

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 two genuinely useful operational facts: the tool is paid ($0.05/call) and requires an API key. It says nothing about latency, error behavior, or what happens for invalid input, so it is only partially complete for a mutation-free but billable call.

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?

A single dense sentence front-loads the purpose and appends the cost/auth caveat in parentheses. Nothing is wasted, though the component list is packed and the billing note is easy to miss.

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?

An output schema exists, so return values need not be explained, and the description covers purpose plus cost/auth. It is still incomplete on sibling routing and on any parameter-level guidance, which is the main gap for an agent choosing among five related tools.

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 description mentions no parameters at all. Reported schema description coverage is 0% at the top level (the single 'birth' property is undocumented), so the description does not compensate for the gap; field-level docs exist only inside the nested AgentBirth def.

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 a specific resource (사주 명식) and enumerates the exact outputs it produces — four pillars, ten gods, 12 stages, jijanggan, gongmang, shensha, relations, daeun. That scope distinguishes it from the narrower sibling day_pillar, though it never explicitly names a sibling.

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?

No when-to-use, when-not-to-use, or alternative routing is given. The agent must infer from the name alone that this is the full-chart tool and that compatibility/day_pillar/monthly/unse are separate concerns.

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 it does disclose two genuinely useful traits: it is a paid endpoint ($0.1 per call) and requires an API key. It also bounds the horizon at 1–12 months. It says nothing about permissions, failure modes, or result shape beyond what the output schema presumably covers.

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 for the core behavior plus a compact parenthetical for cost/auth. No filler, and the primary purpose is front-loaded.

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?

Since an output schema exists, return values need not be explained, and the paid/auth constraint is captured. What's missing is disambiguation from siblings and any format expectation for start_date — moderate gaps for a tool whose parameters are schema-undocumented.

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 effectively 0% at the top level: 'months' and 'start_date' have no descriptions. The description compensates partially by defining start_date's role ('시작일부터') and bounding months to 1–12, but gives no format hint for start_date and no default guidance for months.

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 a specific computation ('운세 흐름') and specifies its inputs and outputs: daily/monthly luck interactions (합·충·형·해·파) with the natal chart over 1–12 months from a start date. This distinguishes it from sibling 'monthly' only implicitly — neither description is visible here, so the agent must infer the split.

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?

No statement of when to choose this over 'monthly', 'saju_chart', or 'day_pillar'. The only operational notes are cost ($0.1/회) and API-key requirement, which are constraints rather than usage guidance.

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