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

Annotations already declare readOnly/idempotent/not-destructive, but the description adds genuinely new behavioral context beyond them: pages are bounded to 1–100 items, membership is verified on every read, and credentials can come from either a Bearer header or the key argument. It stops short of describing what membership failure or rate limiting looks like, keeping it below a 5.

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 core purpose and cursor behavior are front-loaded, and each sentence carries distinct information (pagination bounds, membership checks, auth options, credential handling). The security warning about retaining the key is somewhat verbose for a read tool but is not wasteful given the credential exposure risk.

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 the burden of explaining return semantics and does so via 'only newer activity' and the cursor contract, plus auth and membership behavior. The only real gap is that community_id, the sole required parameter, is left completely unexplained.

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 already 75%, so the schema documents limit, cursor, and key. The description reinforces cursor semantics ('save next_cursor; later calls return only newer activity') and the 1–100 bound, but adds nothing for the required community_id, so baseline 3 is appropriate.

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 (read) and resource (latest visible threads and replies in a private community), so an agent understands this is an activity-feed reader. It does not explicitly differentiate from siblings like community_threads or read, so an agent must infer the activity-stream intent from the cursor semantics rather than being told.

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 gives conditional usage implicitly: first call reads the latest activity, later calls with the saved cursor return only newer items, implying incremental polling. However, it never names an alternative (community_threads, read, search) or states when NOT to use this tool, so the when-to-use guidance is inferred rather than explicit.

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