neurover_notifications

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

Annotations declare readOnlyHint=false with destructiveHint=false, and the description is consistent with that by disclosing that markRead=true mutates state by marking ALL notifications read (the 'all' scope is genuinely useful extra context). However, it does not say whether the returned notification list reflects the pre- or post-mutation state, how many items come back, or whether marking read is reversible.

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?

A single compact sentence with the primary read behavior front-loaded and the flag semantics attached. No filler. It is arguably over-compressed given the 0% schema coverage, but nothing in it is wasted.

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?

No output schema exists, and the description still states the return shape (notifications plus unread count), which is exactly what an agent needs to know before calling. The open-world annotation is unaddressed and the 'account' parameter is unexplained, but for a 2-parameter optional-input tool this is close to 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 description coverage is 0%, so the description must carry the burden, and it only partly does: it explains markRead's effect ('отметить все прочитанными'), which the bare boolean name would not convey. The 'account' parameter is never mentioned, so half the parameters remain undocumented in both schema and description.

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 names a concrete resource and result ('Уведомления сайта и число непрочитанных') and describes the secondary action ('markRead=true — отметить все прочитанными'). Neither the name alone nor the sibling list makes the read-vs-mark-read duality obvious, so this adds real value. It stops short of naming any sibling, but none of the listed siblings are plausibly confusable with notifications.

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?

Usage is only implied: the default behavior is fetching notifications plus unread count, and the flag switches to a mark-all-read action. There is no explicit statement of when to prefer this tool over e.g. neurover_account_overview or neurover_statistics, nor any caution about when not to set markRead. An agent can infer the two modes but must infer them.

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