Unread messages

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

Beyond the readOnly/openWorld/idempotent annotations, it discloses that the tool opens each unread room sequentially, that cost scales with unread count, and that progress is reported per room. This is useful operational behavior an agent could not infer from the annotations alone.

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 with no filler; the core purpose is front-loaded and the cost/progress notes are each distinct. Minor duplication between 'one room at a time' and 'Opens each unread room' keeps it from a perfect score.

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 an output schema exists and the parameter schema documents date and scroll well, the description supplies the key behavioral context an agent needs: per-room iteration, cost growth, and progress reporting. It is complete except for missing sibling-vs-alternative guidance, which is more of a usage-guidelines gap.

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?

The description contains no parameter-level information; date, scroll, and limit_per_room are only documented in the schema. With schema coverage at 67%, limit_per_room is left to its name and constraints, and the tool description adds nothing to clarify it.

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 names the resource ('unread rooms') and the payload ('message bodies') and adds the scoping qualifier 'one room at a time.' It implies retrieval, though it never uses an explicit verb like 'returns' or 'lists,' and it does not explicitly contrast with sibling unread_digest.

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 cost warning ('cost grows with unread count') gives an agent a reason to pause before using this tool, so some usage context is present. However, it never states when to choose this over unread_digest, get_messages, or other siblings, and doesn't give an exclusion condition.

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