數位健康與遠距醫療指南

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

No annotations provided, so the description carries the full burden of behavioral disclosure. It says nothing about what the tool returns (structured data? text? steps?), whether it's a lookup or generator, or any behavioral traits. For a zero-parameter tool with no annotations, this is a significant gap.

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 concise sentence with no waste. It front-loads the technique names efficiently, though the framing is more like a subject listing than an action statement.

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 zero parameters, the description should do more heavy lifting — e.g., clarify the return format or scope. It only lists topics, leaving the agent unable to predict the response shape or use context beyond the sibling set (wellness tools).

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 0 parameters, so per the rubric the baseline is 4. The description correctly implies no inputs are needed, referencing only content topics rather than parameters.

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 specific breathing techniques (方塊呼吸, 4-7-8, 共振呼吸, 生理嘆息) and mentions timing/application, implying it provides relaxation methods. However, it's not a clear verb+resource statement — it reads like a topic label rather than stating what the tool actually returns or does. Compared to siblings like score_gad7 (a clear action), the purpose is vaguer.

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 explicit guidance on when to use this tool versus siblings. The mention of 適用時機 (applicable timing) hints that timing guidance exists in the content, but the description itself gives no when/when-not or alternatives.

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 the underlying method (90-minute sleep cycles) and that output includes age-based sleep-hour recommendations. However, it does not say what happens when both or neither of bed/wake are supplied, nor how latency (sleep-onset time) factors in.

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, well-front-loaded sentence that packs the algorithm, the two output modes, and the supplementary output into minimal text. Nothing is wasted, though it is slightly dense for the amount of missing parameter guidance.

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?

No output schema exists, and the description helpfully notes what the result contains (recommended times plus age-based sleep hours). Still, with three parameters, no annotations, and an unexplained 'latency' input, the definition leaves real gaps for an agent to fill.

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 only 67% and the undocumented parameter is 'latency', which the description never mentions or explains. It also fails to clarify that 'bed' and 'wake' are mutually alternative inputs, so the description adds little meaning 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 gives a specific verb and resource ('依 90 分鐘睡眠週期計算建議就寢或起床時間') plus an extra output detail (age-based recommended sleep hours). No sibling tool deals with sleep, so it is distinguishable from the list, though it 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?

Implying that the user supplies either a bedtime or a wake time ('就寢或起床時間') gives an implicit hint at usage, but there is no statement of when to prefer one mode, no prerequisites, and no alternatives mentioned.

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 must disclose behavior. It reveals the reference date (113-07-01), the 11 situations, and that it reports prescription eligibility and process, but does not state that it is a read-only lookup, its return format, or any limitations. This is partial transparency.

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 a single dense sentence with parenthetical enumerations, front-loading the topic before listing values. It is information-dense with no redundant phrases, though a bulleted list would improve scannability.

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 and no output schema, the description carries the burden. It explains what the tool checks and describes the content of the return (situations, prescription eligibility, process). It does not specify output format or edge cases, but it is sufficient for a low-risk eligibility lookup.

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% and the single 'situation' parameter has no enum or description in the schema. The description fully enumerates all 11 allowed values with Chinese/English explanations and states that omitting the parameter returns all situations, fully compensating 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 states that the tool checks Taiwan telemedicine eligibility, including 11 special situations, whether prescriptions can be issued, and the process, so the resource and scope are clear. It does not differentiate from siblings, but the siblings are unrelated wellness tools. A concise purpose verb is absent but the overall purpose is clear.

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 explicit when-to-use guidance or comparison to alternatives. The description explains the situation parameter values and that omitting it lists all situations, which helps invocation but not tool selection. It lacks conditions for calling this tool versus other 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 full behavioral burden. It is a zero-parameter static list, and the description effectively contains the exact output (the hotline numbers), making behavior fully transparent in content. However, it does not explicitly state that the tool returns these numbers, that it has no side effects, or that it requires no inputs.

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 short sentence front-loads the purpose and lists the hotlines efficiently. No wasted words.

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 simple static reference, the description provides the core content, but given the absence of annotations and output schema, it omits important context such as when to invoke it, that it returns a fixed list, and any safety disclaimers. Adequate but incomplete for an agent in a mental health toolkit.

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 to describe. The baseline for a zero-parameter tool is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies a set of Taiwan psychological crisis hotlines, listing specific numbers. It is distinct from all sibling tools (which are exercises, assessments, or guides), but the phrasing is a noun list rather than an explicit verb+resource statement.

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 explicit when-to-use or when-not-to-use guidance is provided. The crisis context is implied by the term '心理危機求助', but the description does not say to call this tool when a user expresses suicidal ideation or is in acute distress, nor does it reference alternatives.

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 behavioral burden. It implies a static, reference-style resource with no side effects, but it does not explicitly state that the tool is read-only, requires no input, or returns guidance rather than performing an action. For a zero-parameter educational tool the gap is modest.

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 a single compact sentence with no filler, and the three content areas are front-loaded. However, it is phrased as a noun list rather than a clear user-facing action, which slightly reduces structural clarity.

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 informational tool with no output schema, the description names the three covered topics, which is enough for an agent to decide to invoke it. It does not describe the response format or language, but the core content is sufficiently communicated.

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 are no parameter semantics for the description to clarify. Baseline score of 4 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?

The description lists specific content areas (WHO screen time recommendations, phone-reduction methods, health/counseling app privacy checklist), so an agent can tell it is an informational guide rather than an assessment or exercise tool. It lacks an explicit verb like 'provides' and does not directly name sibling tools, but the resource scope is clear.

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 comparison with alternatives such as crisis_lines or the scored mental-health instruments. The agent must infer usage from the tool name and topic list 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?

With no annotations, the description carries the full behavioral burden. It discloses the return (severity) and a scope disclaimer (not a diagnosis), but says nothing about input validation, what happens if fewer/more than 7 answers arrive, out-of-range values, or the severity banding thresholds.

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 plus a short disclaimer. Every clause adds information (scale, item count, return, scope limit) with no filler, and the core purpose is front-loaded.

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

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

For a one-parameter scoring tool with no output schema and no annotations, the description covers purpose, input shape, and the not-a-diagnosis caveat. It still leaves the severity categories and input-validation behavior unspecified, which an agent may need.

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 schema only declares 'answers' as an untyped array of numbers. The description compensates by specifying 7 items on a 0–3 scale, which is exactly the semantics an agent needs to construct valid input, though it omits ordering/omission rules.

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-resource pairing (GAD-7 anxiety symptom scoring), gives the instrument's structure (7 items, 0–3 each), and names the return (severity). The GAD-7 label inherently separates it from siblings like score_phq9 (depression) and score_mood_thermometer.

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?

Offers one usage boundary – '不是診斷' (not a diagnosis) – which tells the agent this is a screening/scoring aid rather than a clinical determination. However, it never says when to prefer this over score_phq9 or the other scoring siblings, leaving selection to inference from the instrument name.

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 discloses what comes back (severity level, recommendation, crisis hotline) and adds a safety caveat that the output is not a diagnosis — meaningful behavioral context. It does not discuss input validation or failure modes, 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?

A single dense sentence that front-loads the instrument and its scoring structure, with the disclaimer last. Nothing is wasted, though the compression makes the parameter mapping slightly hard to parse at a glance.

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 pure computation tool with no annotations and no output schema, the description supplies the input shape, the output contents, and the not-a-diagnosis caveat. Only item ordering and the optionality of the suicide field are left implicit.

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, and it largely does: '5 題 0–4 分' tells the agent that 'answers' is a five-item list scored 0–4, and '自殺意念附加題' identifies the optional 'suicide' parameter. It does not state item ordering or that 'suicide' is optional, so it falls just short of full 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?

Names a specific verb and resource (scoring the BSRS-5 mood thermometer) and specifies the instrument's structure: 5 items scored 0–4 plus a suicide-ideation add-on. The named instrument (BSRS-5) distinguishes it from siblings score_gad7 and score_phq9 without needing to reference them. The closing '不是診斷' sharpens scope.

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 tool name and instrument: call it when you have BSRS-5 answers to score. There is no explicit when/when-not guidance or direction to siblings (e.g., use score_phq9 for depression screening instead), so the agent must infer the 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?

With no annotations, the description carries the full burden. It usefully discloses return content (severity plus an item-9 warning, i.e. a suicidality flag) and a safety caveat that it is not a diagnosis. It does not disclose validation behavior (e.g. what happens if fewer than 9 values or values outside 0–3 are supplied), leaving error semantics 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?

Two compact clauses plus a short disclaimer; the scoring rule and the key warning are front-loaded with no filler. Every element 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?

For a one-parameter scoring tool with no output schema, the description covers input format, output content, and the clinical caveat. The main remaining gap is input validation/error behavior, which matters because a malformed answer array is easy to pass.

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 the single parameter is an untyped-looking array of numbers. The description compensates well by specifying 9 items each scored 0–3, which is exactly the semantic the schema lacks. It stops short of naming the array parameter or mapping items to the nine PHQ-9 questions.

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 (scoring) and resource (PHQ-9 depression symptoms), and explicitly names the output domain (severity, item-9 flag). This cleanly distinguishes it from siblings score_gad7 and score_mood_thermometer, which are different instruments.

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 instrument name and the 'not a diagnosis' caveat, which signals the appropriate screening context. However, there is no explicit when-to-use guidance or routing versus the sibling scoring tools; the agent must infer selection from the name alone.

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