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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds genuinely new behavior: it preserves read state, returns a single page, and instructs the agent to disclose truncation rather than present the page as complete and to paginate before counting. That is actionable, non-obvious agent behavior.

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, each earning its place: identity/scope first, usage trigger second, pagination discipline last. Front-loaded and free of boilerplate.

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?

Output schema and annotations handle return shape and safety, and the description supplies the missing behavioral context (read-state preservation, pagination). It falls short only on parameter semantics, the one gap an agent must consult the schema for.

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 description coverage is only 25% (only workspaceId is documented in-schema), so the description is expected to carry weight for type/limit/cursor. It mentions none of them: no indication that a type enum filter exists, no explanation of limit bounds or cursor pagination semantics beyond 'one page'. The low coverage is not compensated.

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+resource (read notifications), adds the scope 'for the same caller' and the return payload (unread count). The clause 'it does not change read state' implicitly separates it from the sibling mutation tool campaignstack_edit_notifications, so an agent can place it without schema inspection.

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 triggering condition ('when the user asks what needs attention') plus operational guidance about paging through before counting. It doesn't explicitly name an alternative or state when *not* to use it, but the read-state clause rules out the edit tool.

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