cafe-mcp

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds that the tool analyzes shifts across 10-year and yearly luck cycles, which is useful behavioral context but not extensive.

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 sentences with no filler: it states the core subject, then adds an explicit usage signal. Every phrase earns 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?

Given the rich input schema, output schema, and safety annotations, the description is sufficient for an agent to select the tool. It lacks only an explicit relationship to sibling tools or a note about output shape, but those gaps are minor given the structured context.

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 all 15 parameters are documented in the schema. The description adds no parameter-level detail, and it does not need to because the schema already carries the full burden.

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 subject matter — Yin-Yang ratio and climate (調候) balance — and how it shifts across luck cycles. It also gives concrete query examples ('is my chart hot or cold', '조후 분석'). However, it does not explicitly differentiate this tool from the sibling ohaeng_balance, so it stops short of full sibling distinction.

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 description provides clear use guidance with quoted user intents ('is my chart hot or cold', '조후 분석'). It does not mention when not to use the tool or name alternatives, so it is clear context without exclusions.

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?

Annotations already cover the important behavioral profile: readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds the 'classical rules' framing and output contents but no additional behavioral caveats such as handling unknown birth times or limitations. No contradiction with annotations.

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 sentences, front-loads the tool's output, and then gives targeted query examples. There is no filler or redundant restating of the schema.

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 rich input schema, strong annotations, and presence of an output schema, the description covers the core user intent well. The only notable gap is not naming or disambiguating against sibling chart tools, but the description is otherwise sufficient for a read-only lookup tool.

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 input schema has 100% description coverage across all 15 parameters, including legacy alternatives like 'gender' and 'option1'. The tool description does not add parameter-level meaning beyond what the schema already provides, so the baseline score of 3 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 the specific resource (gyeokguk chart structure) and lists concrete outputs: named pattern, grade, body strength, sub-patterns, and the elements behind the judgment. It is clear and actionable, but it does not explicitly differentiate this tool from siblings like saju_chart or ohaeng_balance.

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 description gives explicit use-case examples in both English and Korean ('what is my chart pattern', '내 격국'), which helps an agent select the tool. However, it does not mention when not to use it or name alternative tools for comparison.

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?

Annotations already cover read-only and idempotent behavior. The description adds meaningful context: results are in Korea time, solar-term start times appear only on days when a term falls, and no birth data is needed. This goes beyond the annotations without contradicting them.

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 three sentences: the first lists the calendar contents, the second clarifies no birth data is needed, and the third gives usage examples. No sentence is wasted, and the main 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?

With an output schema present and annotations covering safety, the description is sufficient for an agent to decide when to call and what inputs to provide. It explains the scope (month/day), timezone, and the nature of the data, leaving only input format details to the schema.

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 the baseline is 3. The description's mention of 'month or a single day' and its example queries map to the date and month parameters, but it adds no semantic detail beyond what the schema already states (e.g., date overrides month).

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 (manse-ryeok calendar) and the exact data it returns: day/month/year pillars, lunar date, solar terms with Korea-time start times, and two flag types. It also gives concrete example queries that distinguish it from sibling tools like saju_chart, which require birth data.

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 description provides explicit example use cases ('what is today's day pillar', '이번 달 손없는날', '2027년 2월 일진'), making it clear when an agent should call this tool. It does not name sibling tools or state when not to use it, but the examples are strong enough to guide selection.

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?

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds computational context beyond annotations: hidden-stem weighting and which outputs (dominant, weakest) are reported. No contradiction with annotations.

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 sentences front-load the core output and then give concrete example queries. No filler or repetition of schema information.

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 complex 15-parameter tool, the required input is clear from the schema and the description states the result semantics (weighted distribution, dominant/weakest). The presence of an output schema means return values don't need to be described; only marginal context such as typical use cases is absent, which is already covered.

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 the schema fully documents all 15 parameters. The description adds no parameter-level details, which is acceptable at the baseline.

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 exactly what the tool computes – Five Elements distribution with hidden-stem weighting, plus dominant and weakest element – so an agent can tell it handles element-balance queries. It doesn't explicitly compare itself to sibling tools, but the named terms (五行, dominant/weakest) are distinctive enough.

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: 'which element am I missing' and '오행 분석'. It doesn't state exclusions or alternatives, but for a read-only analysis tool this is clear directional 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds useful context about chart content and foundational role, but it does not disclose operational behaviors such as how unknown birth time is handled, timezone assumptions, or how lunar/legacy parameters affect computation. With annotations present, this is an acceptable but not rich 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?

The description is three sentences with no filler. The first sentence front-loads the chart contents, the second establishes its role relative to other tools, and the third gives concrete usage examples. Every sentence earns its place and the structure is easy to scan.

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 (15 parameters) but the presence of a rich input schema and an output schema, the description does not need to restate parameter details or return values. It provides the key contextual signals an agent needs for selection: what the chart contains, that it is foundational, and example user phrasings. A small gap is the lack of any hint about when not to use this tool or which sibling addresses more specialized chart-reading tasks.

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 the schema already documents every parameter. The description adds no parameter-level meaning beyond what the schema provides. Per the baseline rule, a 3 is appropriate when the schema carries the full semantic burden.

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 clearly explains that the tool produces a Four Pillars natal chart and enumerates the chart components (stems/branches, Ten Gods, hidden stems, five-element ratios, Spirit Stars, Twelve Life Stages). It does not use a direct verb like 'calculate' or 'generate', and it does not explicitly contrast itself with any sibling tool, though labeling it 'the foundation other tools build on' provides some positional clarity.

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 description gives explicit user-intent examples ('show my saju / bazi chart', '내 사주 봐줘'), which tells an agent when to invoke this tool. It also states that it is the foundation for other tools, implying it is the right first step for chart-related requests. It does not enumerate exclusions or alternative tool conditions, so it stops short of a 5.

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?

Annotations already declare readOnly, idempotent, openWorld, and non-destructive behavior. The description adds meaningful beyond-annotation context: it returns only candidates, not a final engine decision, and enumerates the five methods included. That is useful behavioral disclosure not present in the annotations.

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 tight sentences. It front-loads the core resource and scope, adds the critical 'no final engine decision' caveat, and includes practical query examples without any 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?

Given the rich schema, annotations, and output schema, the description is nearly complete: it states the tool's purpose, scope, methods, non-decision behavior, and example user intents. It does not explicitly situate itself against each sibling tool, but the provided usage triggers reduce ambiguity enough.

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 the input schema already documents all 15 parameters and their constraints. The description adds no parameter-level meaning beyond the schema, which matches the baseline of 3.

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 clearly identifies the resource: classical Yongshin (favorable element) candidates from five named methods, with each method's pick. It also explicitly states what the tool does not do ('No final engine decision'), which distinguishes it from any final-answer sibling and makes its scope unambiguous.

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 description gives concrete user-intent triggers ('Use for 'my favorable element candidates', '용신 후보''), which tells an agent when to invoke this tool. It does not explicitly name sibling tools to avoid or state when not to use it, so it falls just short of full usage guidance.

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