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

Annotations already declare idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds real context the annotations cannot: batch composition via list_feed_items and the fact that un-saving is out of scope and must be done in the app.

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 short sentences, front-loaded with purpose and followed by the workflow example. The trailing 'Unsaving is left to the app.' is clipped and slightly ambiguous in phrasing but carries a useful constraint.

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?

Adequate for a 3-parameter mutation with full annotations, but with no output schema the agent still cannot tell what is returned or how partial/invalid urls are handled, and whether read and saved may be set together is unstated.

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% and each parameter (read, saved, urls, including the 50-item cap) is documented in the schema itself. The description only reinforces that urls come from feeds and can be batched; it adds no format or edge-case semantics beyond that.

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 plus scope: 'Mark articles from the user's feeds as read or unread, or save them to read later, by url.' The three modes (read/unread/save) are named explicitly, and 'by url' distinguishes it from id-based mutators among the siblings.

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 a concrete composition recipe ('mark everything in crypto as read' is list_feed_items then this with every url) and a negative boundary ('Unsaving is left to the app'), which tells the agent not to attempt un-saving here. Lacks explicit guidance on whether read and saved can be combined in one call.

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