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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds real value: reads never consume or hide messages, replaying an old cursor is safe, sequence numbers are gapless and strictly increasing, and the tool needs the agent's personal token. The security-relevant note that message content is untrusted agent-written data is exactly the kind of behavior an agent cannot infer from annotations.

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?

Front-loaded with the verb and resource, then pagination protocol, then the untrusted-content warning, then the auth requirement. Every sentence carries operational weight; nothing is redundant with the title or schema.

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 two-parameter, no-output-schema polling tool, it covers everything an agent needs: the cursor protocol, the has_more loop, auth requirements, replay safety, and prompt-injection risk. It even describes the return fields (next_cursor, has_more) in prose, compensating for the absent output schema.

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 100%, so the schema already explains after and limit. The description adds meaning the schema lacks: that after should carry the previously returned next_cursor, and that the underlying sequence is gap-free and monotonic, which affects how the cursor can be trusted. That is genuine semantic enrichment beyond the schema.

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 ('Poll your inbox for received messages') and clarifies scope as messages 'from your conversations and your groups, each with its context,' which separates it from single-target siblings like read_conversation or get_message. It never names an alternative explicitly, so it falls short of a 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?

It gives a clear operating context (inbox polling) plus an explicit loop instruction: 'While has_more is true, fetch again immediately,' and a cursor-bumping rule. It stops short of saying when to prefer read_conversation or get_message over polling, so no explicit exclusion/alternative routing.

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