Recent Thunderbird events

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuine behavioral context: events are buffered, cursors are session-scoped and an old-session cursor is rejected, and `gap`/`resyncRequired` signal lost history. That cursor-lifetime and history-loss semantics are exactly what an agent cannot get from the structured fields.

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 segments: purpose first, then continuation/history semantics. No filler, though the cursor sentence assumes the reader knows what nextCursor refers to and could have been anchored more explicitly.

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 an output schema present, return values need no explanation, and the description covers the non-obvious parts of a polling/streaming tool: buffering, session-bound cursors, and loss-of-history signaling. The missing piece is the meaning of `limit` and whether events are ordered or blocking.

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 0%, so the description bears full burden. It explains cursor (continuation token, session-bound) and since (legacy latestSeq path with a stated limitation), but leaves `limit` entirely unmentioned, so one of three parameters has no semantics anywhere.

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 ('Read buffered Thunderbird notifications') and enumerates the event kinds (new mail, folder and account changes), which is enough to separate it from tb_status or tb_diagnostics. It never names a sibling outright, so the differentiation is inferred rather than declared.

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 implied ('Read buffered... notifications') and operational guidance is given for pagination via cursor=nextCursor. However, it never says when to prefer this over tb_wait (blocking) or tb_status (current snapshot), leaving the closest alternatives unaddressed.

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