Mark all notifications read

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

The description adds significant behavioral context beyond the annotations: there is no undo, the return value `marked` is counted immediately before the bulk update (with a possible race nuance), and the tool deliberately only marks read, with no reverse twin. This goes well beyond the annotations' `readOnlyHint`, `idempotentHint`, and `destructiveHint` by explaining the operational consequences.

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 long but taut—every sentence earns its place: purpose, use cases, caveat, return semantics, and cross-references. It is front-loaded with the core purpose and structured logically, making it dense with operational guidance without any fluff.

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 the tool's complexity, the rich annotations, and the presence of an output schema, the description covers all bases: when to use it, what it does, what to check beforehand, what it returns, and how to reverse the action. No important context for invocation 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?

The input schema already provides 100% coverage for `reason` and `project_id` with clear descriptions. The tool description enriches this by explaining that both parameters 'narrow that blast radius' and 'do not create a preview', plus clarifying the default all-notifications behavior when omitted. This adds meaningful nuance beyond the schema, though it doesn't need to redefine the parameter formats.

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 opens with a concrete verb and resource: 'Mark everything matching the filters as read', with the default scope clearly defined as 'the whole inbox'. It distinguishes this bulk operation from the per-id sibling `mark_notifications` and the read-only `list_notifications`, making the tool's purpose unmistakable.

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?

It explicitly states when to use it ('clear my notifications', 'I have dealt with everything in project X') and recommends previewing with `list_notifications(unread_only=true, ...)` using the same filters first. It also directs the reverse operation to `mark_notifications(ids=[...], read=false)` and warns about the lack of undo, giving clear when-to and when-not-to guidance.

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