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

Annotations already declare readOnlyHint and non-destructive, and the description adds a genuinely useful note ('no lease needed') that tells the agent this is a non-claiming peek. It says nothing about ordering, default page size, whether reading affects handled state, or what fields a preview contains.

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?

Three short sentences, front-loaded with the core purpose, then pagination, then the escalation path and the lease note. No filler.

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, an agent would benefit from knowing roughly what a 'preview' returns, and the cursor naming slip could cost a retry. Otherwise complete for a simple three-parameter read tool whose annotations carry the safety profile.

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 low (33%) — only 'scheduled' is documented — and the description compensates only partially by naming the cursor for pagination, while misspelling it as 'next_after_seq' versus the actual 'after_seq'. Limit bounds, defaults and cursor semantics remain unexplained.

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 ('Get small previews of unhandled addressed messages') with scope qualifiers — previews rather than full bodies, unhandled rather than all — which cleanly separates it from get_message and list_messages.

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?

Explicitly routes the agent: paginate via the sequence cursor and use get_message for full text. It lacks any exclusion statement about when to prefer list_messages instead, so it stops short of full when/when-not guidance.

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