notifications

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

Annotations already declare a safe, idempotent read, so the bar is lower, yet the description adds real value: excerpt text is deliberately omitted, so a follow-up get_issue call is required before acting, and unread-only filtering is the default. It doesn't mention rate limits or the notification-type vocabulary, but the behavioral caveat it does give is the one an agent would otherwise get wrong.

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, front-loaded with what the tool is, then the critical caveat, then defaults. No sentence is filler; each carries a distinct fact.

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?

An output schema exists, so return values need no explanation, and the description still covers the three things an agent needs: the pointer-only return shape, the pre-action read requirement, and pagination/default filtering. Nothing required to call it correctly is absent.

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 'unread_only' default true and cursor paging are already documented in the schema; the description only restates them at a high level. Baseline 3 is appropriate — no new syntax, format, or constraint meaning is added.

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 resource ('Your Linear inbox') plus ordering ('newest first') and the exact shape of each row (ticket, notification type, actor, timestamp). An agent can distinguish it from sibling list tools like list_issues and from the mutating mark_notifications_read without opening any schema.

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?

Explicitly routes the agent onward ('read the ticket with get_issue before acting') and states the default filter and paging behavior. What's missing is a direct comparison point against mark_notifications_read or list_issues, but the when-to-use context is otherwise clear.

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