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

Annotations only declare readOnlyHint=true, but the description adds substantial behavioral context beyond that: unacked-first sort order, cursor pagination, the ack/readAt distinction ('listing never marks messages read'), and the retry semantics encoded in severity levels. This is exactly the kind of disclosure that structured fields cannot carry.

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?

Long but densely packed and front-loaded: purpose first, then pagination and sort order, then the return shape, then the readAt caveat and sibling routing. Every clause (severity table, readAt semantics) earns its place, though the prose is heavy enough to risk skimming.

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, so the description carries the full burden and does so: it specifies the response envelope { messages[], nextCursor } and every field (id, kind, severity, body, actionHint, source, createdAt, readAt). Nothing an agent needs to interpret results or call correctly is missing.

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% for two parameters, so the description must compensate. It explains cursor pagination and the returned nextCursor, which adds real meaning to the cursor parameter, but gives no guidance on limit (default 50, max 200). Partial compensation justifies a mid score.

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 ('List this tenant's system + operator messages') with explicit scope and the three message kinds enumerated. It also distinguishes itself from infrastructure_status as 'the full paginated surface' versus the inline newest 5.

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?

Names the alternative tool and condition: use ack_message to stop a message resurfacing, and infrastructure_status is only the inline 5 while this is the full paginated list. The severity semantics supply clear when-to-act guidance (do NOT retry on 'terminal', retrying the same call works on 'operator_pending').

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