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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description earns credit by adding behavior not in the annotations: it explicitly states that reading does not advance read checkpoints or create an acknowledgment batch, which is meaningful state-side-effect information for a read tool in a messaging system.

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, front-loaded with what the tool returns and followed by the key non-side-effect guarantee. No filler or restated title text.

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?

With no output schema, the description carries some burden for describing returns and does name the payload components (context, responses, attachment metadata). It is still incomplete about window semantics, defaults, and the shape/ordering of the returned context, which matter for correct invocation.

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 only 25%, with just room_id documented, so the description must compensate. It clarifies that number is a room-local message number, but says nothing about the before/after window parameters, their defaults, or the 20-message cap, leaving half the parameter surface unexplained in both places.

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: returns surrounding context, responses, and attachment metadata around a room-local message number. This distinguishes it from read_message and read_attachment implicitly by describing a window of context plus metadata, but it never names those siblings explicitly.

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?

The second sentence implies usage by ruling out side effects ('does not advance read checkpoints or create an acknowledgment batch'), which steers an agent away from ack/catch_up-style tools. However, there is no positive when-to-use statement or explicit alternative named, so the guidance remains implied rather than stated.

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