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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds the meaningful behavioral fact that results default to newest-first and that paging is keyset-based via before_id. It omits anything about response size, cost, or what happens when filters conflict.

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?

The content is front-loaded: the first clause gives ordering, the second gives pagination, and the boilerplate attribution line is short. It is efficient with no wasted exposition, though the marketing/attribution sentence adds little for an agent.

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 ten-parameter tool with geospatial filtering, multiple sort modes, and no output schema, the description covers only the newest-first default and keyset paging; it never describes the returned item shape or warns that offset/before_id interact with sort=distance. The fully-annotated schema prevents this from being a serious failure, but the definition is thinner than the tool's complexity warrants.

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?

With schema description coverage at 100%, the schema already documents all ten parameters including geospatial constraints, sort enum, radius, and limit. The description adds only the default ordering behavior on top of that, which is a marginal contribution, so the baseline of 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?

The phrase "What a feed selects, newest first" conveys that this lists items belonging to a feed in reverse-chronological order, which combined with the name/title makes the resource identifiable. However, it uses no explicit verb (list/get) and does nothing to distinguish it from siblings such as nichedb_recent_items or nichedb_search_items, so an agent cannot tell from the text alone which of those to pick.

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?

The only usage cue is "Page with before_id", which explains how to paginate but not when to choose this tool over the several similar item-retrieval siblings. There is no statement of preconditions (e.g. needing a feed slug from list_feeds, despite the schema mentioning it), no exclusions, and no named alternative.

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