Nonlinear Calendar

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 meaningful traits: deterministic ('Same day → same answer'), public/local/no API key, and quality boundaries ('suggested slots, not a guarantee', 'Preview ≠ prediction', not medical). It does not describe response shape or failure modes, so a 4 rather than 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?

The core purpose is front-loaded, but the text then piles on mixed zh/en trigger lists, slash-separated caveats, and slogan-like fragments ('Preview ≠ prediction') that dilute focus. Some sentences earn their place (scope exclusions), others are redundant boilerplate.

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 3-param, zero-required, no-output-schema tool with no annotations, the description covers what it produces, when to call it, and its behavioral/safety boundaries well. It is largely self-sufficient, missing only return-format or determinism-per-input detail an agent 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 description coverage is 100% and all three params are documented in-schema, so the baseline is 3. The description echoes the task enum values but adds no format, default, or interaction 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?

The description states a concrete output: it 'maps month posture × twelve hours × body load to 2–3 clock windows' for task=deep_work|train|meet|ship|rest. That is a specific verb+resource an agent can act on. The opening 'looks up a deterministic rules engine' framing is meta and slightly obscures the purpose, keeping it short of a 5.

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 explicit trigger conditions with concrete example phrasings (今天什么时候适合运动, when to exercise, etc.) and scopes out related-but-different needs ('Not meds, not glucose, not a diagnosis'). It never routes the agent to a named sibling like today_rhythm or body_rhythm, 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?

With no annotations, the description carries the full behavioral burden, and it does disclose several traits: determinism ('Same day → same answer'), a constraint against inventing pillars/fortune claims, non-diagnostic scope ('Not a diagnosis'), and no auth requirement ('no API key'). These are genuinely useful disclosures, though the compressed form leaves some boundaries ('Adjust ≠ infuse energy', 'Preview ≠ prediction') ambiguous.

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 purpose and determinism claims are front-loaded, which is good, but the body is a string of telegraphic fragments that drift into cryptic slogans ('Adjust ≠ infuse energy', 'Preview ≠ prediction') whose meaning an agent cannot reliably recover. Compact but not every sentence clearly 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?

There is no output schema and no annotations, so the description should ideally describe the shape of the returned rhythm guidance, and it does not. It covers scope, determinism, and safety limits adequately, but a first-time caller still does not know what the answer will look like.

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 schema already documents date, hour, and locale semantics fully, including the default timezone and 时支 format. The description adds no parameter-level guidance beyond what the schema provides, making the baseline 3 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 establishes that this is a deterministic body-energy lookup derived from 'solar term + hour + month posture × sky tightness', which is a specific computation. However, the framing verb is vague ('looks up a deterministic rules engine') and 'body-energy rehearsal' is jargon; it never distinguishes itself from likely-overlapping siblings such as energy_adjust, today_rhythm, or sky_window.

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 trigger phrasings (今晚要不要提前睡 / 今天该不该加练 / 现在这个时辰适不适合动 / train or rest), which clearly tell an agent when to reach for this tool. It stops short of naming a when-not condition or pointing to a sibling alternative, so it falls just below the top band.

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 disclose non-obvious traits: determinism, valid range 1900-2100, public/local/no API key, and output-time constraints (no invented pillars, no fortune claims, no marriage/burial/god directions). It still does not describe response shape or failure modes, but the behavioral disclosure is well above average.

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 core purpose is front-loaded, but the body is a sprawling comma-separated trigger list mixed with partial-sentence prohibitions, and the 'not 宜忌/吉凶' warning is repeated in two different forms. Functional but not tight.

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 compensates by summarizing the return (lunar + ganzhi, then body/work/plan lanes). Combined with the stated date range, default timezone, and no-auth/local operation, an agent has enough to call it correctly; only return-format granularity 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% and all three parameters (date, hour, locale) are already documented in the schema, including the default and range the description repeats. The description adds no syntax, edge-case, or interaction detail (e.g., how hour interacts with the day pillar) beyond what the schema states, so the baseline 3 applies.

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 concrete resource (Chinese almanac / lunar + ganzhi data for a civil date) and a specific behavior (deterministic rules engine, same day -> same answer). The trigger phrases (黄历, tong shu, lunar date, day pillar) make its domain legible, though it never names which sibling (solar_terms, personal_day, today_rhythm) it should be chosen over.

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?

Provides a rich 'call when the user asks...' list covering 黄历/宜忌/lunar date/day pillar/zodiac/solar term style requests, which is clear positive routing guidance. It states what the tool must NOT be read as (宜忌/lucky-day/吉凶), but that is an interpretation guardrail rather than an explicit sibling alternative, so it stops short of full when/when-not routing.

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 full behavioral disclosure and does so meaningfully: deterministic ('Same day → same answer'), no API key required, local, public, and 'Preview ≠ prediction' sets expectations about output nature. It does not describe error behavior or response structure, keeping it short of 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-loaded with the core behavior ('deterministic rules engine') and trims to short, punchy clauses. The Chinese/English trigger phrases and repeated 'Not X, not Y' pattern are slightly dense but each sentence earns its place for an agent trying to match user intent.

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 5-parameter, no-required-arg tool with no annotations and no output schema, the description covers purpose, determinism, privacy posture, and seat distinction adequately. It does not explain what the returned guidance looks like, which is a minor gap given no output schema exists.

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 adds seat-level framing ('personal (sleep/load) or org (window push vs hold)') that maps to the seat enum, but individual parameter semantics (date, hour, month, locale) are already fully documented in 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?

The description specifies the tool as a deterministic rules engine lookup returning energy rhythm guidance, and distinguishes the two seats (personal vs org). It is a bit abstract compared to siblings like activity_window or body_rhythm, but the engine framing and 'personal vs company rhythm' scope are concrete enough to select 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?

Explicitly states when to call, with concrete trigger phrases (能量怎么调 / 个人今天该推还是该收 / 团队这周该不该硬上线 / personal vs company rhythm) and clear exclusions: 'Not HR scoring, not medical treatment.' Nothing is left to inference about the tool's purpose boundary.

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 well: it states determinism ('Same day → same answer'), forbids fabricating pillars/claims, notes 'Public · local · no API key', and frames output as 'Preview ≠ prediction'. Error handling and edge behavior are not covered.

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?

Key behavior and constraints are front-loaded, which is good, but the long middle list of eight-plus trigger phrases in mixed scripts is repetitive and padded. It earns partial credit for structure while being longer than needed.

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, and the description compensates by enumerating the return shape (time atom first line, fold-year line, baseline tone, dated sky marks, do/drop list) plus the follow-up action expected of the agent. That is largely complete for a two-parameter local 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?

Schema coverage is 100% for both parameters (month pattern YYYY-MM with default, locale enum), so the schema already documents them fully. The description adds no syntax, format, or default information beyond what the schema provides, matching the baseline 3 for high-coverage schemas.

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 specifies a verb+resource ('looks up a deterministic rules engine' producing a monthly flow brief with fold-year, tone, dated marks, do/drop list). That is clear and concrete. It does not, however, name or contrast against any sibling such as personal_month or sky_window, so an agent must infer the 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?

It gives an explicit, if sprawling, set of trigger phrases in both Chinese and English (这个月势能怎么样, which days to publish, etc.) that map directly to when this tool applies. No when-not condition or named alternative tool is given, so it stops short of a full routing rubric.

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 real traits: read-only semantics ('reads'), auth profile ('Public · no API key'), env-var fallback behavior, and data-integrity guardrails (don't merge ids, same role ≠ same person, don't invent biographies). It stops short of describing what the read returns or how errors surface, and 'Not L1' is unexplained jargon.

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?

Purpose is front-loaded and every sentence is load-bearing, but the anti-hallucination rule is repeated three times (don't invent people / don't invent a biography / same role ≠ same person), and the opaque 'Not L1' fragment adds noise rather than 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 read-only, no-auth, zero-required-parameter tool with no output schema and full schema coverage, the description covers selection criteria, guardrails, env behavior, and auth. The main remaining gap is any hint of what a successful read returns.

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 both parameters are already documented, including precedence ('Wins over PEOPLE_ROSTER_JSON'). The description restates the people shape and the env fallback rather than adding syntax or format meaning, so the baseline 3 applies.

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?

Opens with a precise verb+resource: 'reads a user-named people roster.' No sibling tool (activity_window, body_rhythm, etc.) does roster reads, so disambiguation is inherent, and the roster scope is stated unambiguously.

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 explicit call triggers with concrete example queries in both languages (这个人是谁 / 花名册 / people roster; before telling a story with named people) and an explicit negative case: if the roster is empty, ask the user to name people rather than proceeding. Nothing 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 full burden and does well: it discloses determinism ('Same day → same answer'), the auth requirement, the specific error code (personal_timetable_requires_key), and the output nature ('Not a fortune verdict'). It omits return-format and any rate/latency behavior, so it stops short of 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?

Dense and front-loaded with the core guarantee ('Same day → same answer') and the call triggers early; nearly every sentence adds a distinct fact (determinism, triggers, personalization, auth, error, non-verdict). The heavy mixed zh/en telegraphic phrasing slightly hurts scannability but is not wasteful.

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 nested-schema, zero-parameter-required tool with no output schema and no annotations, the description covers purpose, invocation triggers, auth, error handling, and the conceptual shape of the result. It does not describe what the response actually contains, which is a modest gap given the absence of an output 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 coverage is 100%, so baseline is 3, but the description adds genuine meaning: it explains the personalization logic (day-master vs today's stem 十神) and clarifies that the hour input contributes an hour-pillar ten-god, which explains why an agent would pass it.

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 (looks up) and resource (deterministic rules engine for a personalized day reading), and positions itself against siblings like personal_month, today_rhythm, and fortune tools by declaring 'Not a fortune verdict.' An agent can distinguish this from the free/broad sibling tools without opening a 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 concrete trigger phrases (我今天怎么样 / 未时基调 / my day) that map directly to invocation, plus a key precondition (BALANCE_API_KEY + birth profile) and the empty-key fallback to 'free tools instead.' The fallback is vague about which sibling to use, and there is no explicit when-not-to-use versus personal_month or today_rhythm, so it falls 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?

With no annotations, the description carries the full burden and does substantial work: determinism ('Same day → same answer'), an anti-hallucination constraint ('Do not invent pillars or fortune claims'), a hard auth requirement (BALANCE_API_KEY + birth profile), and a named error ('personal_timetable_requires_key') with a recovery path. It omits rate limits, latency, and any output 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?

Dense and reasonably front-loaded: determinism and the never-invent rule come first, trigger phrases next, then auth/error handling. The fragment list 'dated sky, sandbox assumptions, fold-memory prompts' is opaque jargon that consumes space without conveying an actionable fact.

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?

Auth, error handling, and determinism are well covered for a zero-annotation tool with a nested birth object. However, with no output schema, the description should convey what the response contains, and instead offers vague fragments ('dated sky, fold-memory prompts') that don't tell an agent what it will receive or how to present it.

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 date, month, locale, and the nested birth object including the gender/dayun rationale. The description only adds that a birth profile is required in practice despite the schema marking it optional, which is marginally useful but below the schema's own level of detail.

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 resource and mechanism: a personalized flow-month computed as day-master vs month stem from a deterministic rules engine. It also draws a boundary ('Not a fortune verdict'), which helps an agent distinguish it from a generic horoscope tool, though it never names the sibling it differs from (personal_day, month_brief).

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 concrete invocation triggers in both languages ('我这个月怎么样 / 我哪周该推进 / my month') and an explicit when-not path (empty key → use free tools instead). It stops short of naming the specific sibling tools to fall back to, leaving the alternative as 'free tools' generically.

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 substantial work: determinism ('Same day → same answer'), access model ('Public · local · no API key'), a hard limit ('Max span 45 days') and a framing caveat ('Preview ≠ prediction'). It stops short of return format or 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?

Dense but every fragment earns its place (determinism, triggers, outputs, access, limit, caveat). The front-load is slightly off—it opens on the 'rules engine' rather than the purpose—but it remains compact and scannable.

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 3-param, read-only, output-schema-less tool, the description covers purpose, triggers, outputs, limits and caveats adequately. Return-shape details are only lightly gestured at by 'lists dated L1 sky marks', but complexity is low enough that nothing essential 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 schema documents to/from/locale and their defaults. The description adds a genuinely param-relevant constraint not in the schema—the 45-day maximum span for the date range—plus intent framing for the locale output, exceeding the baseline 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 names a specific resource—dated sky marks (new/full moon, eclipse, ingress, stations)—and a clear retrieval action, so an agent immediately knows the domain. It does not explicitly contrast with the nearest sibling (solar_terms also returns dated celestial events), which keeps it from a 5.

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?

Concrete bilingual trigger phrases ('新月哪天 / 日食哪天 / 接下来有没有逆行 / what sky events are coming') give clear when-to-call conditions. It also warns against fabricating 'pillars or fortune claims', but names no alternative siblings or when-not-to-use conditions.

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 burden and does it well: deterministic rules engine (same day → same answer), public/local access with no API key, timezone of the term-boundary times (Asia/Shanghai), and the exact shape of the payload (24-term table + next upcoming term). Little behavioral ambiguity remains.

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 purpose, then triggers, then return shape — a sensible order. The bilingual trigger list is long and the 'deterministic rules engine' phrasing is slightly meta, but every element is functional and nothing is wasted.

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-required-parameter lookup with no output schema, the description fully specifies the return contents (civil date, exact term-boundary time, next term) and the year coverage, so an agent needs no further information to call and interpret it.

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 year range (1900–2100) and locale enum are already documented in the schema. The description restates the year range but adds nothing about the locale parameter or formatting behavior, so the baseline of 3 applies.

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 (looks up) and resource (24-term solar-term table) with explicit scope: full table for any year 1900–2100 plus the next upcoming term. An agent can immediately tell this answers solar-term/jieqi date questions, which no sibling tool name suggests it handles.

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?

Provides explicit trigger conditions in both Chinese and English ('二十四节气 / 今年节气表 / 白露是哪天 / 立春哪天 / next solar term / jieqi'), so the agent knows exactly which user utterances select this tool. It also sets a negative boundary ('Do not invent pillars or fortune claims'), separating it from speculative/predictive tools.

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 does so fairly well: it states determinism ('Same day → same answer'), locality and auth ('Public · local · no API key'), output shape, and guardrails ('Do not invent pillars or fortune claims', 'do not invent a biography'). Gaps remain on error behavior and the exact boundary of 'Preview ≠ prediction', but the core behavioral profile is disclosed.

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?

Content is dense and jargoned, and the ordering is stream-of-consciousness ('First line... Then... Then... Then the 12-row table'), so the key purpose is not front-loaded. Most sentences arguably carry information, but the structure impairs quick parsing by an agent.

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 takes on return-value disclosure and largely succeeds, describing the atom line, fold year, Wuhu group, next-year table and the 12-row table. Combined with fully documented schema parameters, an agent has enough to call it correctly, though the jargon-heavy output contract is not fully pinned down.

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 date, month, locale and compact fully. The description adds no parameter-level meaning (no syntax, defaults, or interaction rules) beyond implying day-vs-month use; baseline 3 applies when the schema does the heavy lifting.

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 ('looks up a deterministic rules engine') is vague and borders on restating the title; the actual purpose only emerges indirectly from the trigger phrases (时间折叠 / nonlinear time) and the enumerated output lines. It never distinguishes itself from the many similarly themed siblings (personal_day, month_brief, solar_terms). An agent can guess what it does but not cleanly name it apart from neighbours.

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-call triggers: 'Call when the user asks 时间折叠 / 现在叠的是哪一年 / 这个月对应哪一年 / time folding / nonlinear time / 甲午月是哪一年.' That is explicit invocation context. It stops short of naming alternatives or when-not-to-use cases, so it is not a full 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?

With no annotations, the description carries the full burden and does disclose meaningful traits: deterministic (same day → same answer), local execution, no API key required, and a 'Preview ≠ prediction' caveat. It omits failure modes and rate/edge behavior, but goes well beyond restating the name.

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?

Purpose and determinism are front-loaded, and most sentences carry distinct information (triggers, output sequence, constraints). It is dense and code-switches heavily, edging toward run-on, but little is genuinely wasted.

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, the description usefully outlines the return structure (be time atom, east pillars, fold year, posture × west tightness, daily almanac), which an agent needs. It is fairly complete for a zero-required-param lookup tool, though error/edge behavior is unstated.

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 date, hour, and locale, including the Asia/Shanghai default and enum. The description adds only light context (hour yields the hour pillar), so baseline 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?

States a specific resource and verb: a deterministic rules-engine lookup for today's rhythm (干支/势能/almanac). It clearly conveys the domain and output concept, but does not explicitly differentiate itself from siblings like personal_day, time_fold, or sky_window, leaving the agent to infer the boundary.

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?

Provides explicit trigger phrases in both Chinese and English (今天节奏怎么样 / what is today's rhythm) and an implied negative ('Do not invent pillars or fortune claims'). It gives clear when-to-call context but names no alternative tool or when-not-to-use condition.

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