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

Annotations already declare readOnly=true, idempotent=true, destructive=false, and closed-world, so the safety profile is covered. The description adds genuinely new behavior: results are bounded, restricted to unread items from a 7-day window, and ranked by a stated scoring mix — all relevant to how an agent should interpret output. It stops short of describing ordering specifics or what fields each candidate carries.

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 tight sentences, front-loaded with the hard usage constraint before the behavioral detail and the exclusions. Every sentence carries a distinct instruction; no filler or restatement of the title.

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 one-optional-param read tool with full annotation coverage and no output schema, the description supplies purpose, eligibility window, scoring rationale, and sibling routing — enough to invoke it correctly. The only gap is that the shape/ordering of returned candidates is only hinted at through the scoring list.

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 single 'limit' parameter is fully documented in the schema (1–200, default 100), so coverage is 100% and the baseline is 3. The phrase 'bounded shortlist' loosely signals that the param caps result count, but adds no syntax or trade-off guidance (e.g., cost of raising the limit) beyond the schema.

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?

Uses a specific verb and resource ('Returns a bounded shortlist of unread articles from the last 7 days') and further qualifies it with the scoring dimensions (editorial curation, reading preferences, current revision). It is immediately distinguishable from siblings like get_digest, get_new_items, and search_items.

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 explicit precondition ('ONLY when preparing to curate a newspaper edition with publish_edition'), an explicit exclusion ('Do NOT use for general reading or browsing'), and names the correct substitutes (get_digest, get_new_items). Nothing about tool selection 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.