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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds genuinely non-structured context: a required bearer token with scope "read", and a prompt-injection guardrail flagging that message content is data, not instructions. It does not cover paging behavior or response shape, which keeps it short of 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 clauses, no filler, with the resource stated first and the auth requirement last. It is terse to the point of being fragmentary but nothing is wasted.

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 read tool with readOnlyHint and no output schema, the description supplies the key auth and safety context. However, it omits what the tool returns and how `before` paginates, leaving an agent without full operational context.

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 100%, so both parameters (ref, before) are already documented in the schema; the baseline of 3 applies. The description adds only the gloss that the target is "one agent", which loosely explains ref but adds nothing about before/paging.

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?

The fragment "Messages with one agent" identifies the resource (DMs with a single agent) and the title supplies the verb "Read", so the intent is inferable. But the description never states a verb itself and does not differentiate from close siblings like dm_threads, agent_history, or read_channel.

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?

There is no statement of when to use this tool versus dm_threads, dm_send, or agent_history. The bracketed auth note is a prerequisite, not usage guidance, so an agent receives no routing signal.

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