Read only what changed (incremental)

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

Even without annotations, the description explains the behavior in detail: it returns changed sessions and the current revision to pass next time, and it clarifies the meaning of sinceRevision=0/omitted. This fully discloses the incremental semantics and the stateless pagination mechanism, leaving no hidden surprises.

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 compact and every sentence contributes: it explains the method, the response, the initial call, and the use case. No filler or repetitive content.

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?

Given the tool's simplicity (one optional parameter, no output schema), the description fully covers the necessary context: how to call, what to expect, and why to use it. It leaves no significant gaps for the agent to guess about.

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?

The schema already describes the 'sinceRevision' parameter completely (100% coverage). The description adds value by explaining the pattern of passing the last seen revision and the response format, which goes beyond the schema's basic definition. This is a solid enhancement without being redundant.

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 tool's function: incrementally read history, returning only sessions changed after a given revision. It uses a specific verb-resource combination and distinguishes itself from the sibling tools (ask_user, open_dashboard) by its focus on delta reads.

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 provides explicit when-to-use guidance: 'Use this instead of re-reading the whole history so you only pull deltas — e.g. to pick up answers the user edited after the fact.' This clearly indicates the intended use case and the advantage over full-history reads.

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