Count unread notifications

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds that this is 'one cheap call,' disclosing a performance characteristic, and defines the semantics of unread as 'since you last marked them seen.' This gives useful context that the structured annotations do not provide.

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?

Two short sentences with zero fluff. The purpose is front-loaded and the usage rationale follows in the second sentence. Every word earns its place.

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 simple, side-effect-free read tool with one optional parameter and no output schema, the description covers everything needed: what it counts, how unread is defined, and how to use it efficiently. The agent can safely invoke it without further clarification.

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 input schema fully documents the single optional account parameter with a thorough description, and schema coverage is 100%. The tool description adds no parameter-level information, but it doesn't need to because the schema already carries the full burden. Baseline 3 is appropriate.

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 a specific verb and resource: count how many notifications have arrived since they were last marked seen. It distinguishes itself from get_notifications (the full list) by focusing on the count, so an agent can tell them apart without reading schemas.

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 explicitly advises making this call 'before you pull the full list,' which establishes when to use it relative to get_notifications. It does not name the alternative tool directly or give explicit when-not-to-use conditions, but the context is clear enough for an agent to follow.

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