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

Annotations only declare readOnlyHint=true, so the description's additions matter: it states a login requirement, an authorization boundary (only conversations the caller participates in), the default ordering, and that after= supports polling. It leaves out pagination end conditions (e.g. how to detect no more history) and any rate/quota limits on polling.

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?

Extremely compact — one sentence covering auth, scope, default order, backward paging, and incremental polling — with no filler. The density is close to telegraphic, but every clause carries information an agent needs.

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 four-parameter, read-only list tool with a fully documented schema and no output schema, the description covers auth, scope, ordering and paging modes adequately. It never describes the returned message shape or ordering guarantees after a polling call, and the mismatched 'nextBefore' reference leaves the backward cursor ambiguous.

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% and already documents before/after/limit, so baseline is 3. Worse, the description refers to a parameter named 'nextBefore' that does not exist in the schema (the actual parameter is 'before'), which can lead an agent to pass an invalid argument; the added value is therefore offset by this misleading name.

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 states a concrete verb and resource (reading messages in a conversation) and adds scope (only conversations the user participates in), which tells an agent this is not a global message search. It does not explicitly name sibling tools such as send_message or export_live_messages, so differentiation is only implicit.

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 spells out the two usage modes: default reverse-chronological paging via a before-style cursor, and incremental forward polling via after=messageId. That is actionable when-to-use guidance for the main decision point (paging vs polling), though it gives no exclusions or alternative tools.

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