株主優待 MCP (Yutai MCP)

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 sentinel behavior (interestDays = -1 when settlement cannot make it), that negativeInterestDays grows around weekends, broker-specific liberation rules (SBI/GMO vs Rakuten vs au Kabucom/SMBC Nikko being out of scope), and the YYYY-MM-DD return format. It stops short of auth/permission notes, but for a pure date calculator that is a minor omission.

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 definition is long but strongly front-loaded with the one-line purpose, then organized under bracketed headings for inputs, tradeDate default, and returned fields. Every sentence carries information; the length is justified by the input-format ambiguity, though some field explanations could be trimmed.

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 an output schema exists, the return-value explanations are strictly redundant, yet the description still supplies the domain complexity an agent needs: input normalization rules, the tradeDate default, and broker-conditional liberation schedules. It is essentially complete for correct invocation, only mildly over-explaining outputs.

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, but the description adds real meaning beyond the schema: it enumerates accepted vestingDate formats ("2026-09-30", "9月末", "09", "9", "9月20日", "0920") and explains that month-only inputs resolve to the next upcoming cycle, plus the exact default rule for the omitted tradeDate.

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 opening sentence gives a specific verb+resource: takes a vesting date and returns the dates/days needed for a cross trade (クロス取引). Scope is clear and it implicitly separates itself from siblings by naming estimate_cross_fee's domain (fees) and explaining how the prevYear field pairs with get_benefit, though it never explicitly contrasts the siblings' purposes.

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 concrete when-to-use conditions: tradeDate defaults to 'now' (before/after 15:30 JST, weekends/holidays rolling forward), and prevYear is meant to be matched against get_benefit's negativeInterests / remainingHistories prev data. It does not state when NOT to reach for this tool versus estimate_cross_fee, so it falls short of the explicit-exclusion bar.

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 so thoroughly: it warns that sellMethod=system incurs 逆日歩 risk and that total is only the 逆日歩=0 figure, discloses the note-field caveat for brokers that cannot currently short-sell, and explains that assumptions are echoed back each call. This is exactly the non-obvious behavioral context an agent needs.

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?

Long, but front-loaded with the core purpose and organized under clear 【...】 headings that map to specific concerns. Some segments are instructions to the answering AI about response phrasing rather than tool-selection content, which slightly dilutes focus, but the size is largely justified for a 12-param tool.

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, yet the description goes further and explains the non-self-evident output fields (dates, note, assumptions) and how they should be interpreted. Nothing an agent needs in order to call this tool and interpret 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 description coverage is 100%, so the 12 input parameters are already documented; the baseline is 3. The description adds meaning for output-side fields (vestingDate, lastDayWithRights, exRightsDate, assumptions) but adds little for the actual input parameters beyond what the schema states.

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 (試算する) and resource (株主優待クロス取引の手数料), and the 【対象範囲】 section explicitly bounds the scope to same-broker spot-buy + margin-sell combinations. The siblings (calc_dates, get_benefit, search_benefits) cover entirely different resources, so the agent can route correctly without ambiguity.

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 exclusion (証券会社をまたいだ組み合わせは計算しない) and clarifies which buyMethod/sellMethod cases are in scope. However, it never names an alternative tool for the cases it declines, so the when-not is stated but the redirect 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 carries the burden and does so well: it discloses that negativeInterests/remainingHistories need individually-managed per-stock data, that missing data surfaces a reason in notes, that basic-only avoids fetching heavy data, and it mandates a user-facing disclaimer that 逆日歩 is past data and not predictive. It omits auth/rate-limit/error behavior, so not a 5.

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?

Front-loads the one-line purpose before a well-structured bulleted breakdown of sections. The section bullets are dense but each earns its place given the market-specific terminology (vestingDates, karaDates, systemLendingStatus values); nothing is 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?

For a 2-param tool with an output schema, the description covers everything an agent needs: default behavior, all section semantics, data-availability caveats and the notes fallback, performance characteristics, and a required disclaimer. No material gap remains.

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 the schema already documents both code and sections (including the default and example combinations), so baseline 3 applies. The description's deep per-section content breakdown largely duplicates return-value detail, which an output schema already exists to 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 a specific verb+resource+scope: "銘柄コードで株主優待を1件取得する" — a single-record fetch by stock code. It is clearly distinct in intent from the search-oriented sibling search_benefits, though it never names a sibling explicitly to force that contrast.

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 clear per-section guidance on what each value returns and when to request it (e.g. "逆日歩履歴が欲しいときは [\"basic\",\"negativeInterests\"]"), plus the default (basic) and the lightweight fallback. No explicit when-not or sibling routing (e.g. vs search_benefits), so it stops short of 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?

No annotations exist, so the description carries the full burden and does so well. It discloses non-obvious behavior: netYield is computed only for the last few rows unless sortBy:netYield/minNetYield is set, unretrieved regulation data is treated as 'no restriction', and netYield is absent for stocks with no viable general-credit cross. These are exactly the operational caveats an agent needs.

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 size is large but largely justified by a 57-parameter domain, and it is organized with labeled 【…】 sections and front-loads the purpose before the detail blocks. Some passages (e.g., netYield cost rules) repeat adjacent constraints, so it is not maximally tight, but every block maps to a real decision.

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 an output schema exists, return-format explanation is optional, yet the description still explains details[]/candidates/month-application rules that materially affect answers. Combined with coverage of lendingType, systemLendingStatus, marginRateMultiplier, yield definitions and sort semantics, nothing an agent needs to call 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 the baseline is 3. The description adds real meaning beyond the schema: the vestingDates vs karaDates distinction and the warning not to confuse them, how rarity is derived, and that actualYield may use a different unit than minRequiredUnits/minValue. It clarifies cross-parameter semantics rather than merely restating them.

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 opening line states a specific verb and resource (search shareholder benefits) with combinable filters. It also routes history/inventory lookups to the sibling get_benefit, giving partial sibling differentiation. The core sentence itself remains generic, so it doesn't fully distinguish from calc_dates/estimate_cross_fee without reading further.

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?

Extensive when-to-use guidance is embedded per parameter (e.g., '○月に空クロスが必要な銘柄' → karaDate; '手取り利回り順トップ10' → sortBy:netYield + limit:10). It even gives a when-NOT-to-use warning ('vestingDate で検索しても空クロス対象の銘柄は正しく絞り込めない') and points to get_benefit for histories. It lacks explicit sibling-level exclusion criteria, but condition-to-parameter routing is strong.

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