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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description focuses on behavior beyond that: no cursor pagination, flat rather than grouped shape, and HTML content included by default with token-cost implications. It stops short of describing result ordering or what happens at the limit boundary, keeping it just below a 5.

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 sentences, front-loaded with the core capability before the differentiation clauses, and the trailing follow-up hint is actionable. Slightly repetitive structure ('Unlike X... Unlike Y') but no filler sentences.

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 nine optional parameters, an output schema absent, and rich annotations, the definition covers the essentials: what it returns, how it differs from siblings, and the next step. The only gap is how results are ordered and whether truncation via snippetChars or limit affects completeness of the unread set.

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 100%, so the schema already documents every parameter including defaults and bounds. The description only restates the filter families in prose, adding no syntax, precedence, or interaction details (e.g., whether feedId and folderId combine) beyond the schema. Baseline 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?

States a specific verb and resource ('Returns a flat list of unread articles') and enumerates the filter dimensions (feed, folder, search, bookmarked, date range). It explicitly distinguishes itself from get_digest and list_items, so an agent can pick it without opening any 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 an affirmative condition ('when you specifically need unread articles as a flat list or need article HTML content') and two explicit exclusions with named alternatives (get_digest for grouped, list_items for read items with cursors). It also names the follow-up tool get_item for full article retrieval.

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