Mark all notifications read

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

Goes well past the annotations: discloses the blast radius of the no-argument call, that filters only narrow it and never produce a preview, that there is no bulk undo beyond re-marking individual ids, and that the tool only ever marks read. It even explains the counting semantics of `marked` relative to concurrent arrivals, which no annotation covers.

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?

Front-loaded with the destructive scope in bold and the usage triggers, then the warning, then return values, then rationale and cross-references. Slightly long — the design-rationale paragraph about the absent 'mark everything unread' twin is interesting but not needed to call the tool correctly.

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 zero-required-param bulk mutation, an agent needs to know scope, irreversibility, return shape, and alternatives — all present, and the output fields are explained despite an output schema existing. Nothing material is missing.

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; the description adds genuine meaning by framing both params as narrowing the blast radius rather than scoping a preview, which changes how an agent reasons about them. It does not restate enum values or id formats, leaving that to 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?

First line states a specific verb (mark as read), resource (notifications), and scope (everything matching filters, whole inbox by default). It explicitly distinguishes itself from its closest siblings by naming list_notifications for previewing and mark_notifications for per-id marking.

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 concrete usage triggers ("clear my notifications", "I have dealt with everything in project X") and names the alternative route for a handful of rows. It also prescribes a pre-flight step with list_notifications(unread_only=true) using the same filters, which is unambiguous guidance on when and how to use it.

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