notifications_unread_count

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by flagging the endpoint as lightweight and poll-friendly, which is exactly the operational trait an agent needs for a frequent-call badge check.

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?

Two tight sentences: the first states what is returned and for whom, the second supplies the actionable usage hint. Nothing is redundant and the purpose leads.

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?

There is no output schema, but the description states the return value is a count of unread notifications and notes the authentication scope, which is sufficient for a trivial read. Only a note on response shape (e.g. whether zero is returned as 0) is missing, a minor gap.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-param tool applies. The description correctly implies no inputs are needed beyond authentication context.

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 uses a specific verb and resource ('Get the count of unread notifications') and scopes it to the authenticated user, which clearly separates it from notifications_list or notifications_read_all. It does not name those siblings explicitly, so it falls just short of the top band.

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 gives a concrete usage context — polling to update notification badges — which tells the agent when this tool is the right choice over the heavier list endpoint. It stops short of stating exclusions or naming alternatives explicitly.

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