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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description still adds real value beyond them: the required auth scope and the warning that user-written text arrives in untrusted_fields and must be treated as data, not instructions — a non-obvious output-safety behavior. Pagination behavior is not described, keeping it from a 5.

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 with zero filler: purpose and ordering first, then the prerequisite, then the untrusted-content caution. Nothing redundant or buried.

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 4-parameter read with no output schema and no schema descriptions, the definition covers purpose, ordering, auth and content-safety concerns. It still leaves the pagination contract (how after/before/limit interact, default limit) unexplained, which an agent needs in order to page correctly.

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% across 4 parameters, so the description must compensate. "By sequence number" usefully clarifies that `after`/`before` are sequence cursors rather than timestamps, but `limit` and `conversation_id` semantics are left entirely to the bare 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 ("List a conversation's messages") plus the ordering key ("by sequence number"), which clearly separates it from the sibling list_conversations and get_conversation. It does not explicitly name those siblings, so the differentiation is inferable rather than stated.

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?

"Needs `inbox:read`" gives a prerequisite, and the scope of the tool implies its use case (read the messages inside one conversation). However, there is no guidance on when to prefer list_conversations to discover a conversation_id, or how this relates to mark_conversation_read or send_message.

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