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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds genuinely new side-effect information: it explicitly will not advance read checkpoints or open an acknowledgment batch. That is exactly the kind of post-call state caveat annotations cannot express, though the return structure itself is only summarized.

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 tight sentences, front-loaded with what is returned and followed by the key non-side-effects. No filler or redundant restatement of the title.

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 annotations covering safety and no output schema, the description handles the "what and what-not" adequately for a read tool. However, for a four-parameter tool with low schema coverage, missing before/after windowing semantics and any note on result shape leaves real gaps.

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 only 25% — just room_id is documented — so the description needs to carry before, after and number. It implies a window around "number" but never explains that before/after bound how many neighboring messages are included or what their 0–20 caps mean in practice.

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 gives a specific verb and resource — it returns context, responses and attachment metadata around a room-local message number. The scope ("around a message number") is clear, though it does not explicitly distinguish itself from look-alike siblings such as read_around or read_attachment.

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?

Usage is only implied: the negative statement "does not advance read checkpoints or create an acknowledgment batch" hints that ack covers that case, and "nearby context" hints at read_around overlap. There is no explicit when-to-use-this-vs-alternative routing.

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