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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the agent knows this is a repeated-safe state mutation. The description adds scope context by spelling out that mark_all covers "everything unread for the brand", but says nothing about irreversibility, permissions, or the effect of re-marking an already-read notification.

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 two-sentence preamble is front-loaded with the selection rule, and the Args block is short and scannable. Slight redundancy between the preamble and the Args list prevents a 5.

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 four-parameter mutation with no output schema, the description covers the required selector rule, the brand scoping, and both operating modes. What is missing is the return behavior and any authorization requirement, but the destructive annotation carries much of the risk signalling.

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 only 25%, so the description must compensate, and it does: it documents brand_id as required and explains what notification_ids and mark_all actually do, plus the selection constraint that the schema does not encode. Only the analytics-only user_intent parameter is left to the schema's own 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 states a specific verb and resource ("Mark notifications as read") and immediately scopes it by mechanism (specific IDs or all unread for a brand). It is clear without opening the schema, though it never distinguishes itself from the read-only sibling get_notifications or the other manage_* mutation tools.

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 real usage guidance for the two parameter modes and states the mutual requirement ("One of the two is required"), which is the main operating rule. However, it offers no when-to-use guidance versus alternatives such as get_notifications, and no exclusions or prerequisites are mentioned.

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