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

Beyond the readOnly/idempotent annotations, the description discloses ordering (newest first), per-item unread state, an aggregate unread count in the response, the absence of a side effect (does not mark as read), and an authentication requirement ('takes signing in'). These are exactly the behavioral facts an agent needs before calling.

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 core meaning is front-loaded in the first clause, and every later clause carries information (ordering, unread totals, non-marking, auth). The enumeration of notification types is somewhat padded and ends weakly with 'and the like', which is the only real bloat.

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 two-parameter read tool with no output schema, the description covers what is returned (ordered items, unread flags, total unread) and the auth prerequisite. Pagination mechanics are left entirely to the schema, which is acceptable since coverage is complete.

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 100%, so both parameters (page with 20-per-page paging, unread_only) are already fully documented in the schema. The description adds no syntax or edge-case detail about them, so the baseline 3 applies.

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 and resource (gets the notifications), scopes it to the authenticated user ('the person who connected the app'), specifies ordering ('newest first'), and enumerates the notification categories covered. It also implicitly separates itself from mark_notifications_read by stating that reading here does not mark items read.

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 line 'Reading them here doesn't mark them as read' gives clear context for when this tool is appropriate versus the sibling mark_notifications_read, and the unread_only parameter is documented in the schema. It stops short of an explicit 'use X instead when Y' routing statement, so it is strong but not fully prescriptive.

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