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 by structured data. The description adds genuine behavioral context beyond that: default sort order, cursor-based pagination, and the cost/payload tradeoff of detail levels. It leaves out pagination-termination semantics and whether section and since compose.

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?

Four short sentences, front-loaded with purpose and ordering, then filtering, then paging, then the detail optimization. Every sentence carries distinct, actionable information with no padding.

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 still conveys the ordering guarantee and the cursor field to page with, and annotations cover the read-only profile. For a 5-parameter list tool it is nearly sufficient, missing only limit behavior and any indication of response shape beyond article ordering.

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 the load and it mostly does: since is explained as an ISO timestamp meaning "published after your last read", cursor as the paging handle, and detail=headline as the cheap scan mode. limit and section are never mentioned in the description (section values are at least self-evident from the enum), and the response cursor is named next_cursor while the request parameter is cursor, a minor naming mismatch.

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 published articles") plus scope ("published", not drafts) and ordering ("newest first"). This is clearly distinguishable from get_article (single item) and list_sections (taxonomy) among its siblings. An agent can pick it without opening a 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 concrete usage patterns: filter by section, use since for incremental reads after a last read, page with the returned cursor, and use detail=headline to scan cheaply. It does not, however, state when NOT to use this tool or point to get_article for full-text retrieval, which is the obvious alternative.

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