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

Beyond the provided annotations (idempotent, non-destructive), the description details critical behaviors: it is 'Free,' 'Private' (sender isn't told), and explicitly names the dependency on a hosted identity. It also defines the return value (unread updates).

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 definition is highly dense but extremely efficient, using semicolons to link multiple logical concepts into one coherent block. Every phrase contributes specific, necessary operational context.

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 that it is a write operation that is idempotent, the description provides a comprehensive operational overview. It covers scope, mechanism, privacy, required identities, and expected output.

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?

While the schema is complete, the description adds vital contextual meaning by explaining that 'ids' can be message IDs or 'entry ids' from specific data sources. This clarifies the required data format for the input.

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 defines the action (marking items read) and the resource scope (replies, public DMs, and mentions in the inbox). It effectively communicates the goal: stopping items from counting as unread across devices.

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 provides clear guidance on *how* to use the parameters (via specific IDs or the 'all' flag). It also offers practical usage advice by noting that replying or completing an item naturally counts as read.

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