Trend

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

The annotations already establish that this is a safe read-only, closed-world lookup. The description adds meaningful behavioral context beyond them: it describes what data is included (latest day, category column, rank, prior-year line, clue) and explicitly states that raw search-volume values are omitted, though it does not cover error behavior or rate limits.

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 compact and front-loads the core concept before adding terms-of-use information. The bilingual repetition is slightly redundant but not wasteful enough to outweigh the efficient structure.

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, annotations cover the safety profile, and the single parameter is fully documented. The description still supplies useful semantic context about the returned data and the omission of raw search volumes, leaving only minor gaps around how this tool relates to its 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?

There is only one parameter, and the schema already documents it at 100% coverage with an example. The description reinforces that the input is a shopping search keyword, but it adds little syntax or format detail beyond the schema, so the 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 identifies a specific resource: one shopping keyword from the trend shopping surface, shown on the most recent day it appeared, with rank/column context. It is much more concrete than a tautology, but it does not explicitly distinguish itself from the sibling tools 'repository' and 'today'.

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 description implies that this tool is for looking up a single keyword, but it gives no explicit when-to-use guidance, no exclusions, and no comparison to the available alternatives 'repository' and 'today'.

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 cover readOnlyHint=true and openWorldHint=false, so the description adds real value beyond them: it discloses the 30-day/article eligibility filter that can make the call return nothing, explains that kind/line are AI-written only when listed in ai_written (otherwise the repository's own GitHub description), and notes the license is only present when the article leans on one. It does not discuss error behavior for unknown repositories.

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 return-value inventory is front-loaded and specific, but the text is long and the trailing English sentence largely restates the preceding Korean clause, producing redundancy rather than added information. The parenthetical figure list also bloats the opening 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 an output schema present, the description need not explain return shapes, yet it still enumerates the fields and — crucially — the eligibility restriction that governs whether a call returns data at all. Combined with one fully documented parameter and safety annotations, an agent has enough to invoke it correctly.

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?

There is a single parameter at 100% schema description coverage, and the schema already gives the format (owner/name, e.g. vllm-project/vllm) and accepts a GitHub URL. The description adds no additional meaning about the name argument, so the baseline of 3 applies.

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

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

The description states concretely what the tool returns: one GitHub repository's page on trend.ondo.sh, with its figures, kind/line, date, figures_read_on, address and optional license. That is far more specific than the bare name 'repository', and it is clearly distinguished by scope from the keyword and today siblings (single repository vs. keyword lists vs. daily view), though it never names those siblings.

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 eligibility rule ('only repositories that trended on GitHub in the last 30 days or have an article are answered') tells the agent when the call will succeed, which is useful. But nothing says when to pick this over keyword or today, and no prerequisites or fallback behavior are 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context: what 'since' means, that only fields in ai_written were AI-authored, and that kind falls back to the repo description. It does not discuss freshness limits or response shape, so a 3 is appropriate.

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 extremely long and dense, with substantial Korean/English redundancy and field-by-field detail that overlaps the output schema. It is not front-loaded – the core purpose is buried inside enumerations of headline/rank/commerce fields. Several sentences do not earn their place against structured fields that already exist.

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 spends most of its length re-describing them while omitting sibling routing and call-time context. For a two-world page tool it is broadly sufficient, but the imbalance leaves real gaps.

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 (date, world enum) are documented in the schema itself. The description does not add syntax or format detail for the parameters beyond restating the two worlds; it spends its parameter-adjacent words explaining return fields and the 'since' concept. Baseline 3 is correct.

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 the resource: the day's page on trend.ondo.sh, split between the 'github' (trending repos) and 'commerce' (Korean shopping searches) worlds. The specific verb is implicit ('get/return the day's page') rather than stated, but an agent can infer it. It does not distinguish itself from the sibling tools keyword/repository.

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 guidance on when to call this versus the sibling keyword or repository tools, and no prerequisites are stated. The only usage hint (date defaults to the most recent day) comes from the schema, not the description. The agent is left to infer selection on its own.

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