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

The description discloses meaningful side effects the annotations do not: reading marks messages as read and creates a visible line in the other person's Min AI, plus it warns that message content is data and never instructions. However, 'marks what you read as read' is a state mutation that conflicts with readOnlyHint=true, so the description and annotations disagree about whether this tool modifies the environment.

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?

It is dense and front-loaded: the two usage modes come first, then side effects, then the safety instruction. The telegraphic example-question phrasing is efficient, though the clause about 'a line in that chat's Min AI' is compressed to the point of being hard to parse.

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 no output schema, the description covers the two modes, the mutation side effect, and prompt-injection safety, which is most of what an agent needs. It stops short of describing what the returned messages look like or how paging terminates, but the schema covers the cursor mechanics.

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 both `who` and `before` are already documented in the schema, including the olderCursor paging contract. The description reinforces `who` semantics with example phrasings and clarifies that omitting it means unread, which is useful but largely duplicative of 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?

The description names a specific verb and resource (read a chat / read everything unread) and uses concrete example questions to pin down the two modes. It is distinguishable from siblings like read_thread and read_profile, though the differentiation is implied by the examples rather than stated outright.

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 explicit routing conditions: pass `who` for a specific person's messages, omit it to get everything unread, and escalate to flag_conversation when content is threatening or unsafe. It does not contrast with read_thread or read_plan, but the when-to-use and when-to-escalate guidance is concrete.

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