Japan News Headlines (NHK) MCP

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 signals a subscriber/pro tier via 'PRO', which loosely maps to the access_token requirement, but says nothing about return format, result limits, or failure behavior for unpaid access.

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 terse fragments with essentially zero waste, and the tier marker is front-loaded. It is efficient, though the fragmentary style borders on under-specification rather than polish.

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 one undocumented parameter, the description should do more. It omits what a result contains, how many are returned, and how this differs from the two sibling headline 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?

Schema coverage is 50%: access_token is documented in the schema, and the description partially compensates for the undocumented category param by listing its accepted values. That is real added meaning, but it doesn't clarify whether the list is exhaustive or what happens with an invalid value.

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 ('headlines for a category') and enumerates the category values, which is genuinely useful. However, it is a noun phrase with no verb, and it doesn't distinguish itself from the sibling top_headlines — 'top' even appears in the category list, creating ambiguity about which tool returns the general top feed.

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 use this versus headline_search or top_headlines. The 'PRO' marker hints at a paid tier but says nothing about prerequisites beyond that, and no exclusions or alternatives are named.

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 discloses source coverage and the 'up to 40 hits' result cap, which is useful behavioral context. However, it omits return structure, ordering, failure behavior, and subscription/rate-limit implications beyond the vague 'PRO' label.

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 core action and scope. The unexplained 'PRO.' prefix adds ambiguity without enough payoff, but otherwise the sentence is 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?

For a simple two-parameter search tool, it gives the data source and result cap. But with no annotations and no output schema, it should say more about what a hit contains, how results are ordered or limited, and whether subscription/auth is strictly required.

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 50%: access_token is documented in the schema, but keyword is not. The description adds only that keyword filtering exists, without explaining matching semantics (title/body, multiple terms, case, etc.).

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 (keyword filter/search) and resource (major NHK RSS categories), with a useful result cap. It does not explicitly distinguish itself from siblings category or top_headlines, and the leading 'PRO.' is unexplained.

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 choose headline_search over category or top_headlines. The only hint is the 'PRO' label, which is not explained as a precondition or exclusion.

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 does carry some load: it discloses the fixed 5-item limit and signals that the call takes no filters, plus 'FREE' hints at no cost/quota. It says nothing about update cadence, ordering freshness, or what a response entry contains.

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 fragments, front-loaded with the cost signal and the result cap. Nothing wasted, though 'FREE.' in caps reads as marketing rather than specification.

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 tool the description covers the essentials: source, recency, and result count. Only the freshness/ordering behavior is left 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?

The tool takes zero parameters, so there is nothing for the description to clarify; baseline 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?

States a specific resource (latest NHK top-news headlines) with a concrete result cap (first 5), which is enough to distinguish it from headline_search and category, 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?

No when-to-use guidance and no mention of the sibling tools. The agent must infer that this is the unfiltered browse option while headline_search is for queries and category for topic scoping.

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