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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description still adds genuinely new behavior: the pagination model of two independent cursors that must both be advanced to stay current, which is not derivable from the annotations.

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 with the directive front-loaded and nothing wasted. The first clause is a telegraphic noun list rather than a full clause, which slightly hurts readability but keeps it compact.

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 bears more of the burden for describing what comes back, and it only sketches the content categories without format or termination guidance. It is adequate for a two-param, fully-annotated read tool but leaves the cursor fields and the shape of the response under-explained.

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 0% and the description only alludes to the parameters as "both cursors." It never explains the distinction between `after` and `memory_after` or the unit/semantics of the integers, so it fails to compensate for the undocumented schema.

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?

Names the concrete content returned – chronological encounters, attributed shared-memory revisions, and recent conversation roots – so the agent knows this is a combined catch-up feed rather than a single-stream reader. It is distinguishable in spirit from siblings like read_shared_memory or read_encounters, but it never names those siblings to make the boundary explicit, which keeps it short of a 5.

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?

"Start here" functions as a clear usage directive marking this as the entry point, and "follow both cursors to catch up" tells the agent how to consume it. There is no statement of when NOT to use it and no alternative tool is named, so it gives clear context without exclusions.

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