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. '探查' implies a read-only inspection, and the enumeration of probed categories hints at what comes back, but there is no statement of latency, permission needs, or side effects (printer probing can trigger OS-level calls) — a meaningful gap for a zero-annotation 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?

A single front-loaded sentence naming the capability and its four scopes with zero filler. It is terse rather than padded, though the terseness borders on under-specification for a tool with no annotations and no output 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?

With no output schema, the description must convey the return shape; listing the four probed categories does this at a high level, but it omits usage context and any indication of result structure. Adequate as a minimum-viable probe tool, not complete.

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 and additionalProperties is false, so there is nothing for the description to disambiguate. Baseline 4 applies; no parameter-level value could be added.

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 (探查/probe) and resource (本机交付能力/local delivery capabilities), then enumerates the probed domains: printer, browser, PDF tools, channels and policies. The domain is clearly distinct from the kb_*/review_*/paper_*/learn_* siblings, though no sibling is named for 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?

No statement of when this should be called, no prerequisites, and no routing to alternatives. An agent gets no signal that this is typically a pre-flight check before paper_build or paper_deliver, which would be the natural usage.

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 burden. It never states that this is a read-only listing, what ordering or pagination applies, what happens when filters match nothing, or what 'limit' defaults to — significant gaps for a tool with zero annotation coverage.

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 short parenthetical line with no wasted words, and the resource is front-loaded. But at four undocumented parameters it is terse to the point of under-specification rather than efficient.

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 annotations, no output schema, 0% schema description coverage, and four parameters, the description covers only a fraction of what an agent needs. Nothing says what an 'atom' record contains or how results are ordered or bounded.

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%, so the description must compensate. It names three of the four parameters (subject, tier, status) as filters, which is genuinely useful, but adds no format or accepted-value detail and ignores 'limit' entirely. Partial compensation for a 0%-coverage 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 resource ('原子清单' / atom list) and a filtering capability, which is a recognizable verb+resource shape. However, 'atom' is unexplained domain jargon and the description does nothing to distinguish this from the overlapping siblings kb_search, kb_overview, or kb_chapter.

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 guidance on when to use this listing tool versus kb_search or kb_overview, and no exclusions or prerequisites. The filter hint implies a browsing use case but never says so explicitly.

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?

无 annotations，描述需承载全部行为说明。仅说明了返回内容，但未提及权限、副作用、是否缓存、最大字符限制行为等。'读单章'暗示只读，但未明确安全性或错误处理。

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?

极简一句话，前置动词和返回内容，无冗余信息。

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?

对于 3 参数、无输出 schema、无 annotations 的工具，描述仅提供了基本用途。缺少参数说明、使用场景和只读保证，但核心功能清晰。

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?

3 个参数，schema 描述覆盖率仅 33%（仅 chapter 有描述）。description 未补充 subject 和 max_chars 的语义（例如 subject 是分类还是过滤条件，max_chars 如何影响输出）。在低覆盖率下，描述未起到补偿作用。

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?

明确说明动词和资源：读取单章并返回章节全文与结构化原子/组合行。能区分于 kb_overview、kb_search、kb_atoms 等兄弟工具（后者侧重概览、搜索或原子），但未提及其与 kb_atoms 的边界。

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?

没有说明何时使用本工具而非 kb_atoms 或 kb_search，也没有前提条件或排除场景。用户只能假设当需要完整章节内容时使用，但描述未明说。

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 behavioral burden. It discloses the shape of the returned aggregate, which is useful, but never states that the operation is read-only with no side effects, nor any cost, caching, or scope caveats for a tool that scans the whole knowledge base.

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 front-loaded sentence naming the tool's domain followed by a compact field list. No filler, no redundancy, and the most important information (what you get back) leads the clause.

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 does the work of enumerating the returned fields, which is the key thing an agent needs for an aggregate tool. It stops short of clarifying whether counts are scoped to the caller or the whole corpus, 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?

Schema description coverage is 100% – the single optional 'subject' filter is already documented in the schema as 只看某个科目（可选）. The description adds nothing about the filter's semantics or accepted values, 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?

States a specific resource (知识库) and enumerates exactly what the overview contains: subjects, chapter counts, atom counts, tier and status distribution. This clearly separates it from the narrower kb_chapter/kb_atoms/kb_search siblings, though it never names them explicitly.

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 word 总览 (overview) implies 'use this to get a summary,' but there is no explicit when-to-use statement, no mention of alternatives like kb_search or kb_atoms, and no prerequisites. Usage is inferable only from the noun.

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 burden. It does disclose two genuinely useful traits: the operation mutates _INDEX.md (a write, not a read) and it is 幂等 (idempotent), so re-running is safe. However it says nothing about preconditions (must chapter files exist?), failure behavior, or whether other index content is touched.

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 compact sentence with the target (_INDEX.md statistics table) and the mechanism (recompute from chapter files) front-loaded, plus the idempotency qualifier in parentheses. Zero wasted tokens.

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-argument tool with no output schema and no annotations, the description covers what it does, which file it mutates, and that the operation is repeatable. The remaining gap is the operational trigger — when in the kb workflow this should be invoked relative to kb_validate/kb_chapter.

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 and the schema confirms this with additionalProperties=false, so there is nothing for the description to disambiguate. The baseline of 4 applies; no parameter-level value could be added.

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 verb pair (重算回写 = recalculate and write back) and a concrete resource (_INDEX.md's statistics table), which is far more specific than the bare name kb_reconcile. It does not explicitly distinguish itself from neighbors like kb_validate or kb_overview, so it stops 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?

Usage is only implied: the mention of recalculating from 章节文件 (chapter files) hints it should run after chapter content changes, but there is no explicit when-to-use statement, no when-not-to-use, and no named alternative among the many kb_* siblings. Adequate but leaves the agent to infer the trigger condition.

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 burden. It usefully discloses the return content (file:line and status), which matters since there is no output schema, but says nothing about scope, matching behavior, permissions, or limits. Some value added, significant gaps remain.

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 with the action front-loaded and no wasted words. Terseness here is efficient, though it borders on under-specification rather than optimal brevity.

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 5 parameters (0 required), 20% schema coverage, no annotations, and no output schema, a one-sentence description is not enough. It omits any explanation of tier/status/subject/limit and provides no usage context relative to the many kb_* siblings.

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 only 20% (only query is documented as AND-matched keywords). Four of five parameters (tier, limit, status, subject) are undocumented in both schema and description, and the description adds no semantics for them. It does not compensate for the low coverage.

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 (检索/search) and resource (原子/组合/章节 = atoms/combinations/chapters), plus what it returns (file:line and status). It is clearly a keyword search, but it does not explicitly differentiate itself from siblings like kb_atoms or kb_chapter that also target those resources.

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 phrase 一次命中检索 hints at a one-shot lookup, but there is no statement of when to use this versus kb_atoms, kb_chapter, or kb_overview, and no prerequisites or exclusions. The agent must infer selection from sibling names alone.

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 burden. It never says whether validation is read-only or mutates state, whether a failure blocks downstream tools, what permissions are needed, or what the pass/fail output looks like. 'Quality gate' hints at a verdict but discloses no actual 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?

A single colon-delimited fragment with no wasted words, but it is under-specified rather than genuinely concise: no verb, no sentence structure, and the reader must parse a bare noun list. Compact but not well-formed.

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 tool with two undocumented parameters, no annotations, and no output schema, the description is far too thin. It does not explain the pass/fail semantics of a gate, the scope of each check, or the interaction with siblings like kb_reconcile, leaving the agent unable to call it confidently.

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% for both parameters. The description is completely silent on 'limit' and 'index_check' — it never indicates whether limit caps findings, whether index_check toggles one of the four named checks, or what defaults apply. It does not compensate for the coverage gap.

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 fragment '知识库质量门禁' (knowledge-base quality gate) plus a list of four check categories conveys that this validates KB integrity, but no verb is stated and the name kb_validate has to carry the action. The four checks (structural contract, reference integrity, ledger reconciliation, provenance anchors) give an agent a rough idea of scope, but it is not sharply differentiated from kb_reconcile.

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 run this gate, whether it must precede a build/deliver step, or how it differs from kb_reconcile despite the overlapping '状态账目对账' (ledger reconciliation) concern. The agent is left to infer invocation conditions entirely.

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 one real side effect: the prediction is written to a prediction log (预测写入预测日志). Beyond that it says nothing about permissions, reversibility, or what a prediction result looks like, leaving most behavioral traits undocumented.

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 single parenthetical is tight and front-loads the core action, but at this length it is under-specified rather than genuinely concise for a six-parameter tool. Nothing is wasted, but too little is said.

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 six-parameter tool with no annotations, no output schema, and zero parameter documentation, the description is far too thin. An agent cannot determine what to pass for atom, tier, event, hint, or next, nor what the prediction 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?

Six parameters with 0% schema description coverage means the description must compensate, yet it explains none of them. The phrase about writing to a prediction log only faintly gestures at the `log` parameter; atom, hint, next, tier, and event are entirely opaque in both schema and 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 states a concrete action and object: predicting the pass probability before answering, with the prediction recorded to a log. This is a specific verb+resource rather than a restatement of the name. It does not, however, distinguish itself from siblings like review_grade or learn_report.

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?

"先预测后作答" (predict first, then answer) implies the ordering context in which the tool is used, which is useful sequencing guidance. But no alternatives are named and no conditions for when-not-to-use it are given, so usage is only implied.

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 burden of behavioral disclosure, and it largely fails. It does not say whether the report is computed on demand, whether the write parameter persists state (a potential mutation), whether ablation triggers expensive recomputation, or anything about auth/permissions. Only the topic list hints at what is produced.

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?

It is a single compact line with no wasted words, but it is a noun phrase fragment rather than a front-loaded sentence with a verb, so it reads more like a section list than an actionable description. Adequately sized but structurally weak.

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 annotations, no output schema, and 0% parameter coverage, the description is the only source of information and it omits the write/ablation semantics and any indication of return shape. For a tool with side-effect-implying flags, this is insufficient.

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% for both parameters. The description's mention of 变体消融 (variant ablation) loosely maps to the ablation flag, but the write flag is completely undocumented in both schema and description, leaving half the parameter surface unexplained.

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 resource (学习算法报告 / learning algorithm report) and enumerates the report's contents — ability/difficulty, calibration, pattern risk, teaching-method ranking, variant ablation — which is more than a tautology. However it lacks a verb (generate? return? compute?) and never distinguishes itself from siblings like learn_predict, so an agent must infer that this is the aggregate reporting endpoint.

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 use this tool versus the many siblings (learn_predict, review_due, review_grade, etc.), nor any prerequisite or trigger condition. The agent is left to guess that this is the summary/report view after other learning steps.

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 behavioral burden. It usefully discloses that the answer and paper outputs are separated, but says nothing about where files are written, whether existing artifacts are overwritten, or what permissions/side effects apply to this generation operation.

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 compact sentence that is front-loaded with the core action and then the outputs. Nothing is wasted, though the terseness leaves behavioral and usage gaps unaddressed.

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 tool with a complex nested spec object, no annotations and no output schema, the description should say what is returned (paths? inline content?) and how the generated artifacts are delivered. It states the artifact types but omits the return contract entirely.

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 the single nested spec object is documented inline (title/subject/paper/questions with stem/answer/atoms/work_mm), so the schema does the heavy lifting. The description adds no parameter-level meaning beyond what the schema already provides, which is the baseline 3 case.

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 (出一张卷 / produce a paper) and names both output artifacts (卷面 HTML and 答案 md), so the agent knows what it creates. It does not differentiate from the sibling paper_deliver, leaving the boundary to inference.

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 when-to-use guidance and no mention of alternatives. The obvious sibling paper_deliver is never referenced, so the agent gets no help deciding which of the two paper tools to invoke.

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 supplied, so the description carries the full disclosure burden. It never says that printing is an external, hard-to-reverse side effect, whether files are written and where, or what permissions/printer availability are required — significant omissions for a tool whose policy can trigger a physical print.

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 phrase with no filler, and the formats are listed compactly. Its brevity, however, reflects under-specification rather than disciplined editing.

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 a nested object parameter, no output schema, no annotations, and zero schema description coverage, so the description must do all the work — yet it only restates the formats. An agent cannot determine what 'spec' should contain or what happens on delivery.

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% across all three parameters. The description lists delivery formats that partially map to the 'policy' enum, but it never names the parameter, and the nested 'spec' object and 'printer' parameter remain completely unexplained.

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 pair (generate paper + deliver) and a resource, plus the concrete delivery formats (print/PDF/HTML/text). It does not distinguish itself from the sibling paper_build, which sounds like it also produces a paper, so an agent could confuse the two.

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 when-to-use guidance, no statement of prerequisites, and no routing to alternatives such as paper_build. The phrase '按环境交付' hints that the channel is chosen by environment, but this is left for the agent to infer rather than stated.

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, but it discloses nothing about read-only vs mutating behavior, whether quota consumption or state changes occur, or what the return shape is. It only hints at the tier/score structure of the items.

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 very short and front-loads the resource, but it is a noun fragment in parentheses rather than a structured sentence. Its brevity reflects under-specification rather than efficient communication.

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 review/scheduling tool with no annotations and no output schema, the description supplies almost none of the information needed to invoke it correctly: no verb, no usage context, no parameter meaning, and no behavioral disclosure.

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% for three parameters. '每日配额' loosely maps to `quota`, but `date` and `subject` are not addressed at all, and no formats, defaults, or constraints are provided, so the description does not compensate for the schema gap.

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 resource ('到期复习项' / due review items) and adds scope via the parenthetical ('分层 A/B/C + 分值档 + 每日配额'). However, it is a noun fragment with no verb, so it is unclear whether the tool lists, returns, or marks items, and it does not explicitly distinguish itself from the sibling review_grade.

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 guidance is given. The description does not state the context in which this should be called, nor does it mention review_grade or any other alternative, so the agent must infer the selection criteria.

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 supplied, so the description carries the full burden. It does disclose that the write fans out to four targets (review queue, chapter status grid, event stream, _INDEX reconciliation), which hints at multi-effect mutation, but says nothing about auth requirements, reversibility, or what dry_run/sync_index actually change.

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?

It is extremely short, which is good in principle, but it is a compressed colon-plus-list fragment rather than a front-loaded sentence. Brevity here reflects under-specification rather than efficient communication.

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 7-parameter mutation tool with zero annotations, no output schema, no required-field guidance, and 43% schema coverage, a single telegraphic line is wholly inadequate. An agent cannot safely determine what will be written or under what conditions.

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?

Seven parameters with only 43% schema coverage, and the description adds no parameter meaning at all. The four undocumented ones (atom, note, dry_run, sync_index) leave the agent guessing about the key inputs, including whether dry_run prevents any mutation.

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 fragment '判定写回' does convey a specific action (writing a verdict back), and the following list names the targets touched. But the phrasing is telegraphic jargon with no sentence structure, and nothing separates it from siblings like review_due, learn_report, or kb_reconcile, which plausibly overlap with the review/queue/reconciliation domains.

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 indication of when this tool should be called instead of alternatives, nor any precondition, trigger, or exclusion. With siblings such as review_due and learn_report that could each be the right entry point for recording study outcomes, the absence of routing guidance is costly.

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 behavioral burden. It lists what the plan aggregates but says nothing about whether the call is read-only, whether it mutates any state, whether it requires auth, or how '断点' (breakpoint) is determined. Only content composition is disclosed, not 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?

It is a single terse phrase with no wasted words, so it is concise and front-loaded. However, the brevity is achieved through under-specification rather than efficiency, leaving key concepts (quota, breakpoint) unexplained.

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 two-parameter tool with no annotations and no output schema, the description is too thin: it neither explains the parameters nor clarifies the return/plan structure, and it does not address behavior at all. It is a content label rather than a usable tool definition.

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 neither parameter is referenced in the description. The roles of 'date' (plan target date?) and 'quota' (cap on items?) are entirely undocumented, so the description fails to compensate for the coverage gap.

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 what the tool produces (today's plan) and enumerates its composition: due reviews, uncleared wrong questions, and breakpoints/resume points. That is a specific resource with meaningful scope beyond the name. It stops short of differentiating itself from the sibling review_due, which appears to cover one of the same components.

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 when-to-use guidance, no prerequisites, and no mention of alternatives such as review_due or review_grade. The agent must infer that this is a daily-planning aggregator purely from the name and the component list.

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