List categories and labels

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

Annotations already provide readOnlyHint=true. The description adds that each entry includes an unread count, which is behavioral context beyond the annotation. However, it does not mention ordering, pagination, or any limits, but given zero parameters and simplicity, this level is adequate.

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 description is two sentences, front-loaded with the core action after the verb 'Lists', and every sentence adds distinct value. No redundancy or filler.

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?

Given no output schema and zero parameters, the description explains what is returned (categories, labels, unread counts) and a practical note about addressing by name. It is complete enough for a simple list tool, though it could mention if there is any default ordering or maximum items.

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?

There are no parameters, so the baseline is 4. The description does not need to add parameter information, and it correctly uses the space to explain the return content rather than inventing param guidance.

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 description clearly states the tool lists categories and user labels with unread counts, and clarifies the difference between categories (folders for feeds) and labels (tags for articles). It also notes they are addressed by name in other tools, fully distinguishing its purpose from sibling tools like list_feeds or get_unread_counts.

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 description implies use for retrieving category and label names with unread counts, and mentions they are used by name elsewhere, but does not explicitly state when to use this tool versus alternatives such as list_feeds (for feeds) or get_unread_counts (which might focus on aggregate counts). No direct when-not or alternative guidance is provided.

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