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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds useful context: 'bounded' indicates a limited scope, and 'Unavailable tombstones contain no removed content' clarifies what to expect from tombstones. The note about reusing cursors with the same filters is a behavioral detail that helps the agent avoid mistakes. These additions go beyond the annotation and are valuable.

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?

The description is two sentences with no wasted words. The primary purpose is front-loaded in the first sentence. The second sentence adds a critical usage note about cursor reuse and tombstone behavior. It is concise and readable, though it could arguably be more structured with explicit parameter mentions.

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?

The tool has 4 optional parameters and an output schema. The description gives some context about the nature of the data (public changes, replies, bounded, tombstones) but does not explain the parameters or how they filter results. Since the schema provides no descriptions, the agent lacks essential information to call the tool correctly. The output schema exists but the input semantics are under-specified, making the description incomplete for effective usage.

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 0%, so the schema provides no descriptions for the parameters. The description does not explain what 'room', 'actor', 'limit', or 'cursor' mean or how they affect the call. The only indirect hint is about cursor reuse, but it does not define the cursor parameter itself. With zero coverage and no compensation, the description fails to convey parameter semantics.

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 clearly states the verb 'read' and the resource 'bounded public changes or replies to an actor'. It conveys a specific action and scope. However, it does not explicitly differentiate from sibling tools like browse_frontpage or catch_up, which might also read public content. The term 'bounded' is somewhat vague but gives a hint of a paginated or limited view.

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 description offers no guidance on when to use this tool versus alternatives. It mentions cursor reuse ('Keep the same filters when reusing a cursor') but does not explain the context for selecting this tool over others. There is no mention of alternative tools or conditions that would make this tool the right choice.

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