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

Even though readOnlyHint=true already signals safety, the description explicitly states 'Read-only: this never marks anything read', clarifying a key side-effect boundary. It also exposes ordering, payload contents, and the read-status field, going well beyond the annotations.

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 compact but information-dense, leading with the core purpose and then adding filters, return fields, and the read-only guarantee. Every sentence contributes, and nothing is redundant with the schema.

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?

There is no output schema, so the description carries the burden of explaining return values; it details each entry's fields, categories, pagination, and filter behavior. For a read-only list tool with simple parameters, this is fully sufficient.

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 coverage is 100%, so the baseline is 3, but the description adds value by explaining category examples ('audit_failed'), defining unread_only as 'what nobody has looked at yet', and describing pagination with limit/offset in prose. It complements rather than merely repeats the schema.

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 states a specific verb and resource: 'Read the organization's notification feed', and specifies sorting ('newest first') and subject matter ('what finished, what broke, and what changed'). It also enumerates concrete categories and differentiates from generic polling, making the tool's purpose unmistakable even among many siblings.

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 gives an explicit use case: 'catch up at the start of a session' with example questions, and contrasts it with 'instead of polling every website'. It also explains how to filter with category and unread_only, giving an agent clear direction on when and how to invoke it.

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