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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavior beyond that: the default 24-hour window when no cursor is supplied and the cursor-chaining model, which an agent cannot infer from annotations. No output schema exists, but the returned change categories are at least enumerated.

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 sentences, zero waste, front-loaded with what the tool returns and followed by the cursor contract. Every clause carries information an agent needs.

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?

For a read-only polling tool with two optional params and no output schema, the description covers the returned categories, the default time window, and the cursor chain. It is nearly complete; termination/pagination end conditions are only implied by the reference to next_cursor.

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 100%, so the baseline is 3. The description adds real meaning beyond the schema: since_cursor is defined as originating from the previous call's next_cursor, and the no-cursor case resolves to a 24-hour window — semantics the schema does not state.

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+resource ('Changes since the last check') and enumerates what is returned: completions, failures, blocked milestones, new proposals, new manager tasks. That distinguishes it from generic siblings like list_activity, but it never explicitly names or contrasts with the closest alternatives (list_activity, whats_waiting, get_summary), so differentiation is partial.

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?

Gives concrete invocation guidance: pass next_cursor from the previous call as since_cursor, and without it you get the last 24 hours. That is clear context for how to call it, but there is no when-to-use/when-not guidance against sibling tools, so it stops short of a 5.

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