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

With no annotations, the description carries the full load and does well: it discloses payload size (~a few KB vs multi-megabyte /feed.json), the hard 20-item window ceiling, newest-first ordering, and truncation semantics for `since` that predates the window. What it leaves implicit is the read-only/no-side-effect guarantee (only implied by 'poll it safely') and any auth or rate-limit expectations.

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 sentences, front-loaded with the resource and ordering, then the cost/safety rationale, then the alternative. Every clause earns its place; the '/feed.json' comparison is a compact way to convey cost.

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?

There is no output schema, so the description's enumeration of returned fields (dek, split counts, chain ids) fills that gap, and it covers windowing, ordering, truncation, and the older-data escape hatch. Nothing an agent needs to call or interpret this correctly is missing.

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 100%, so all four parameters are already documented in the schema, including the limit ceiling and the truncated behavior of `since`. The description only restates the filter axes ('date, kind, or chain') without adding format or edge-case detail beyond what the schema carries, so the 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 ('the 20 most recently published pieces, newest first') plus the exact payload fields returned: dek, computed split counts, story-chain ids. It names what it is not — the multi-megabyte /feed.json — so an agent can separate it from the heavier feed sibling 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?

Explicitly frames the use case ('the cheap "what moved since I last looked" call', safe for a scheduled agent to poll) and gives an exclusion with the alternative: 'For anything older than the window, use list_audits with a date range.' The chain-id source is also routed to get_chain.

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