MagReader article discovery

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description usefully clarifies that only a preview is returned and full content lies outside the service, but it omits whether the preview is truncated, what the referral link entails, or any access conditions.

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 that are reasonably front-loaded, with the primary operation stated first and the scope caveat second. Nothing is redundant, though the second sentence is slightly vague about 'outside this discovery service'.

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 one required parameter, no output schema, and full annotation coverage, the description does enough to convey the general shape of the return (preview plus referral link). It falls short by not explaining the required articleId or where it comes from, which is the key missing piece for correct invocation.

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, articleId, with 0% schema description coverage, and the description never mentions it at all. It doesn't say what an articleId is, its format, or that the caller must supply one, so the schema's pattern constraint carries the entire burden.

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 verb 'Get' and object 'public preview' plus 'agent referral subscription link' give a rough sense of the operation, but it never states it retrieves a single article by ID, leaving the resource somewhat ambiguous. It also bundles two outputs (preview and referral link) without clarifying their relationship, so an agent can't fully distinguish it from search_articles at a glance.

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 second sentence functions as a scope boundary ('full content and subscription purchases are handled outside'), implying this is a discovery-only call, which is useful. However, it never explicitly says to use search_articles to find an articleId or when this tool is preferred over it, so the routing is left to inference.

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, and openWorldHint=false, so safety is covered. The description adds a genuinely useful constraint that only public metadata and publisher teasers are returned, which tells the agent not to expect full subscription content. However, it says nothing about pagination mechanics, result limits, or ordering beyond the vague "next".

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?

Three short sentences, front-loaded with purpose and followed by return-scope and continuation hints; almost no waste. The only slightly muddled element is the unmapped "next" reference.

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 well to state what is returned (public metadata and teasers), but it leaves the cursor/continuation contract ambiguous by calling it "next" and says nothing about result volume or what a teaser record contains. Adequate for a simple search tool, but not complete.

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 carry parameter meaning, and it does not: neither 'query' (length limits, syntax) nor 'cursor' is explained. Worse, it refers to "next" as the pagination handle while the actual parameter is named 'cursor', which risks a wrong or confused invocation.

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 ("Search published articles") and adds meaningful scope detail: matches inside subscription articles are included. It doesn't name the sibling get_article_preview, so the distinction from it is only implied by the word 'search'.

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 sentence "Follow next to search older archive sections" gives a hint about iterating results, but there is no explicit when-to-use guidance and no comparison to get_article_preview. The agent must infer that this is the entry point and get_article_preview is the follow-up.

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