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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds real behavior on top: public REST representation, pagination totals and next/previous links, how to continue paging, and that results include publication-filtered relationships and public links. The notable extra is the explicit 'content is never silently truncated' guarantee, which tells the agent how to interpret a large result set. It stops short of describing auth requirements 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?

Front-loaded with the list/search duality and the browse condition, then the return shape and the alternative tool. The writing is dense and near-telegraphic, but each clause adds information; nothing is filler.

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 correctly carries the return-shape burden by naming pagination totals and next/previous links, plus the pagination continuation rule. Remaining gaps are minor, such as how slug filtering interacts with q or what the sort modes mean beyond the enum.

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 67%, so the schema already documents q, slug, sort and author_id. The description adds meaning beyond it for page ('increment page to continue') and per_page ('large pages may require a smaller per_page'), which the schema does not explain. It says nothing extra about slug, sort or author_id, so it is not fully compensating for the remaining coverage 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?

States a specific verb+resource ('List or search published articles') and immediately scopes it to the published collection. It also distinguishes itself from the sibling get_article by name ('Use get_article for a known ID'), so an agent can route without opening either schema.

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?

Gives the browse-vs-search condition explicitly ('Omit q to browse all records') and names the alternative tool for the lookup case. It also warns about the per_page tradeoff for large pages, so both the choice of tool and the choice of parameters are guided.

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