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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: results are ordered newest-first and the response carries an unread count, which matters since there is no output schema.

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 short sentences, nothing wasted, and the resource plus ordering are front-loaded before the parameter hint.

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?

With no output schema the description usefully describes the return shape (notifications plus unread count), but for a 2-parameter tool with 0% schema coverage the unexplained limit parameter and absence of any pagination or when-to-use guidance leave real gaps.

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 parameter burden. It explains unread_only's meaning but says nothing about limit (range 1-60, default 20) or result truncation behavior, leaving one of two parameters undocumented.

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 specific resource (the user's in-app FirmLedger notifications) and its ordering (newest first) plus the included unread count, which clearly separates it from the mutating sibling mark_notifications_read. It never names that sibling explicitly, so it stops short of full sibling differentiation.

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?

"Set unread_only for just the unread ones" implies when to toggle the flag, but there is no guidance on when to call this tool versus mark_notifications_read or other siblings, and no mention of pagination or limits.

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