awesome-student-ai-skills

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

With no annotations, the description does carry real behavioral weight: it discloses that a local rendering script is executed and that output defaults to outputs or /tmp when output_path is omitted. It does not disclose overwrite behavior when output_path already exists, failure modes for an invalid skill_name, or filesystem/permission implications of writing a file.

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 purpose sentence followed by a tight parameter list, with the conditional note about demo mode attached directly to the data parameter. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need no explanation, and the description covers all five inputs plus default-path behavior. The remaining gap is the undocumented shape of the `data` dictionary and which sibling tool produces it, which matters for correct pipeline sequencing.

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 0%, so the description must compensate, and it largely does: every one of the 5 parameters is explained, school enumerates accepted template values (tsinghua, pku, whu, zju, default) that are absent from the schema, and skill_name gives example values. The only shortfall is that the valid skill_name set is open-ended ('等') and must be discovered via list_student_skills.

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 and artifact: it renders structured application data through a local script into a standard .docx. That is concrete and distinguishable from siblings like list_school_templates or simulate_student_review, but the description never explicitly contrasts itself with them or says which upstream tool supplies the data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: you generate after having collected structured data, and demo=True is offered as a fast trial path. There is no explicit statement of when to prefer this over route_student_skill or get_skill_requirements, nor any prerequisites such as 'run get_skill_requirements first'.

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 bears the full burden. '获取' unambiguously marks this as a read operation, and the description names what is returned (元数据与配置), which is the key behavioral fact. It does not say what happens if skill_name is unknown (empty result vs error), nor does it mention any side effects or permissions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short lines with the purpose front-loaded and the parameter note second; nothing is padded. The '参数:' block is slightly redundant with the schema but the examples earn their 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?

For a single-parameter lookup with an output schema, return values need no explanation, and the description covers the input well. What is missing is routing context against the large sibling set, particularly get_skill_requirements, which an agent could easily confuse with this 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 0%, so the description must compensate — and it does, giving the parameter's meaning plus three concrete example identifiers ('innovation-research', 'national-scholarship', 'challenge-cup') that reveal the expected naming style. It stops short of stating whether the name or the alias form is accepted, or case sensitivity.

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: 获取 (get) 指定申报材料赛道的详细元数据与配置 (detailed metadata and configuration of a given application track). An agent knows exactly what is returned conceptually. However, it does not distinguish itself from the sibling get_skill_requirements, which sounds like a closely overlapping lookup.

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 implied by the name and description — it is the metadata lookup for a named skill — but the description never says when to call this instead of get_skill_requirements, list_student_skills, or route_student_skill. No prerequisites or exclusions are given.

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 burden. It discloses the shape of the response (required items, field specs, scoring pitfalls) and its position in the workflow, but says nothing about whether it is read-only, whether results are cached, or what happens with an invalid or unknown skill_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?

Two short sentences plus a compact parameter note, with the purpose and the pre-write trigger front-loaded. There is no filler, though the parameter block slightly duplicates the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return-value details need not be spelled out, and the description covers purpose, timing, and parameter intent adequately for a single-parameter read tool. The main remaining gap is the absence of a valid skill_name list or error behavior.

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 explains skill_name as the track name and supplies two concrete example values ('innovation-research', 'national-scholarship'). It falls short of enumerating all valid values, leaving the agent to guess a valid identifier.

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+resource (获取指定赛道的信息采集清单) and enumerates what the checklist contains (必填项、字段规范、评分避坑要点). It is clearly distinct from siblings like get_skill_info or generate_student_doc, though it does not explicitly contrast itself with them.

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 trigger: call this before writing the user's application document to obtain the list of key information that must be asked of the user. That is clear usage context, but it does not name alternatives or state when not to use it (e.g. versus get_skill_info).

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 burden of behavioral disclosure. It communicates that only currently built-in supported templates are listed and gives examples of their formatting properties, but it does not explicitly confirm read-only safety, side-effect behavior, or availability constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences with no wasted language. It front-loads the core action and then adds useful examples of supported formatting details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter list tool with an output schema, the description is nearly complete: it explains what is listed and gives examples of supported template features. The main minor gap is that it does not explicitly relate this tool to document generation workflows or state that results are limited to built-in templates only.

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 has zero parameters, so there is no parameter semantics burden. A baseline of 4 is appropriate because the description does not need to explain inputs, and it correctly focuses on the resource being listed.

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: listing built-in university-specific typesetting style templates. It also clarifies scope with examples of supported universities and formatting aspects, making it clearly distinct from sibling tools such as generate_student_doc or skill-related tools.

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 implied: an agent would call this to discover available school templates, likely before generating a document. However, the description does not explicitly state when to use it versus alternatives such as generate_student_doc, nor does it mention any prerequisites or exclusions.

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

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

No annotations are provided, so the description carries the full burden. The word '列出' (list) makes the read-only nature obvious and the risk is minimal, and the total count (35) hints at the result size; however, it says nothing about ordering, pagination, or whether an invalid category errors or returns empty.

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 first line front-loads purpose and scope; the parameter block is structured as a bulleted value list that is easy to scan. Slightly long for one parameter, but every enumerated value carries real disambiguation value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value shape need not be described. For a single-optional-parameter enumeration tool, the description covers everything needed to call it correctly; only edge-case behavior (unknown category, empty results) is left unspecified.

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 0% — the input schema defines `category` only as a bare nullable string with no enum or description. The description fully compensates by enumerating all nine valid values with concrete Chinese examples for each (e.g., 'challenge cup / internet+ / red-tour tracks' for competition), which is exactly what the schema omits.

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: '列出所有支持的高校学生申报书与申请材料赛道（共 35 个）' — an enumeration of supported student application/declaration tracks, with the count given. It is clearly distinguishable from detail-oriented siblings like get_skill_info or get_skill_requirements, 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 verb 'list' implies usage as a discovery/entry point, and the optional filter suggests it can be used to narrow before routing. But there is no explicit 'use this when…' guidance, no mention of when to prefer route_student_skill or get_skill_info instead, and no prerequisites 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?

No annotations are provided, so the description carries the full behavioral-disclosure burden. It implies a read-only recommendation operation, but does not state whether it has side effects, what permissions are needed, whether results are deterministic, or how it behaves with vague queries. The default top_n=3 is the only concrete behavioral detail.

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 examples are front-loaded, then the two parameters are listed compactly. The parameter section is useful because the schema lacks descriptions, though it repeats names already visible in the schema. Overall it is appropriately sized.

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 is simple, has only two parameters, and has an output schema, so return-value explanation is not required. The description covers purpose and parameter meaning adequately. However, it does not explain how this routing step relates to sibling workflow tools such as generate_student_doc, nor does it provide behavioral caveats.

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 is the only source of parameter meaning. It explains query as natural-language intent/keywords and top_n as the number of recommended tracks, including the default of 3. It does not state top_n bounds or query length limits, so it is strong but not complete.

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 action and resource: matching a student's intent/query to the top N suitable application material tracks. The examples clarify the intended input domain. It does not explicitly distinguish itself from sibling tools such as list_student_skills or get_skill_info, 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?

The examples imply when to use the tool, namely when a student describes a goal or need in natural language. However, it gives no explicit when-not guidance or comparison with alternative sibling tools. Usage is inferable but not fully guided.

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, and it does substantial work by disclosing what the tool returns, including the veto warning and plagiarism pre-check, which are non-obvious behavioral traits. It does not say whether the simulation is read-only or stateful, how long it takes, or which skill_name values are valid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two purpose sentences followed by a compact parameter list; the output enumeration is front-loaded and every clause conveys information an agent needs. No filler or repetition of structured fields beyond the useful glosses on the ambiguous parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be spelled out, yet the description leaves open how text and data interact (precedence, whether both may be passed) and where skill_name values come from (likely list_student_skills). For a tool where only skill_name is required, an agent could invoke it with no reviewable content and get nothing useful.

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 0%, so the description must compensate, and it defines all three parameters: skill_name is the track name with concrete examples ('innovation_research', 'challenge_cup'), text is the application body, and data is the structured application dictionary. It omits the critical constraint that at least one of text/data must be supplied, given only skill_name is required by 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 first sentence names a specific verb and resource (execute a review simulation and score a student's application text or data), and the second enumerates the concrete outputs (dimension scores, overall grade, judge comments, veto warning, plagiarism pre-check, improvement suggestions). None of the siblings (list_*, get_*, route_*, generate_student_doc) overlap, so an agent can distinguish it, though the description never explicitly contrasts itself with an alternative.

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 by the subject matter: you call it when you want a simulated review of an application. There is no statement of when to prefer it over generate_student_doc, no prerequisites, and no exclusion criteria, so the agent must infer the trigger conditions.

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