LingoDew

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety and locality are covered. The description adds the content scope (a fixed set of product facts) but no traits beyond that, such as whether the answer is static or fresh; for a zero-parameter informational tool that is an acceptable but not rich disclosure.

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 with the subject ('Product facts about LingoDew') first and the covered topics after; 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?

For a zero-parameter, no-output-schema lookup, the description gives enough scope for an agent to decide when to call it. It could be marginally stronger by noting the answer is a static product summary, but 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?

The tool takes no parameters, so the baseline is 4; the description correctly implies a no-argument call by framing it as a fixed lookup of product facts. Nothing about parameters needs further elaboration.

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 specific resource and enumerates what it covers: features, platforms, pricing and free tier. It is clearly distinct from the sibling tools (channel_stats, find_videos, word_in_videos), which operate on video data rather than product metadata, though it never states that contrast 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?

Usage is only implied — an agent can infer this is the tool for questions about the product itself, but the description contains no explicit when-to-use or when-not guidance and names no 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?

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds value beyond that by disclosing what the payload contains (per-level speed, rank, topic share) and that the channel must be in LingoDew's library, which is behaviorally relevant context an agent would otherwise have to guess.

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 that leads with what is measured, then lists the metric set, then closes with the use case. No filler, no repetition of the title.

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 carries the burden of describing return content and does so thoroughly. What remains unclear is what 'level' means as a discrete value and what happens when a channel is not in the library — minor gaps for a two-parameter read-only 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 description coverage is 100%, with both parameters documented and an enum for language, so the description need not explain them. The phrase 'per level' is not a parameter and adds no clarification about how channel identifiers are matched (name vs id vs URL). 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?

The description names a specific resource (a YouTube channel in LingoDew's library) and enumerates the exact metrics returned: video count, per-level speaking speed, rank, video share and main topics. This is clearly a stats-retrieval operation, distinct from find_videos and word_in_videos, without needing to name 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 states a concrete use case: 'Useful for picking channels that suit a learner's level.' That gives clear context for when to reach for it, but there is no explicit when-not guidance or pointer to a sibling alternative.

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?

Annotations already declare readOnlyHint, non-destructive and openWorldHint=false; the description usefully reinforces the closed-world nature by saying videos are 'on LingoDew' rather than a live web search, and it discloses the return shape (titles, channels, levels, links, tappable subtitles). It omits any mention of result-count limits or empty-result behavior, 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?

Two compact sentences with zero filler: filters first, return contents second. Every clause (language, level scale, topic, keywords, return fields) carries information an agent can act on.

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 job of explaining return values and covers all filter dimensions, so an agent can call it correctly. The only gap is the limit parameter (default 10, max 25) and pagination/truncation behavior, which is invisible in the description.

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 80%, so level/query/topic/language are already documented in the schema, and the description mostly restates the same level-to-framework mapping (JLPT N5–N1, CEFR A1–C2). The 3-parameter baseline applies; nothing new about limit or matching semantics is 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 ('Find') and resource ('real YouTube videos on LingoDew') with the exact filter dimensions (level, topic, keywords). It is clear about what the tool returns, though it never explicitly differentiates itself from siblings like word_in_videos or channel_stats — the distinction is only implied by the resource.

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 described filters (level/topic/keywords for a language-learning search), but there is no explicit statement of when to prefer this over word_in_videos or channel_stats, and no mention of prerequisites or when not to use it.

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?

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so safety is covered. The description adds valuable context that annotations cannot carry: exactly what data comes back and that a word page with native-audio examples is included. It does not cover behavior for unknown words or missing data, 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 core question ('how often is a word heard') and then enumerates the metrics. No filler, though the enumerated metric list makes it run long within one sentence.

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 only two required params, no nested objects, and no output schema, the description carries the return-value burden and does so by listing the metrics and the linked word page. Nothing critical is missing for correct invocation, though expected behavior for a word absent from the corpus 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 coverage is 100% and both parameters are documented in the schema (word forms for Japanese/English, language enum). The description's mention of 'Japanese or English word' and 'heard' only echoes the enum and hints at spoken-corpus matching; it adds no syntax or format detail beyond the schema. 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 specific resource and scope: word frequency (number of videos, occurrences, coverage, rank, level) across LingoDew's video corpus. It is clearly distinguishable from siblings like channel_stats and find_videos. It is phrased as a noun description rather than a verb, but the intent is unambiguous.

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 statement, no exclusions, and no mention of sibling tools. Usage is only implied by the described output (a vocabulary/corpus statistics lookup), so an agent must infer the trigger conditions itself.

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