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

readOnlyHint=true is consistent with a read-only delta feed, so the annotation already carries the safety profile, and the description usefully reinforces the polling contract ('pass the cursor from the previous call'). It does not disclose what happens with a stale/expired cursor, whether the response is capped, or how the next cursor is surfaced, which matter for a polled endpoint with no output schema.

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, both earning their place: the first states what is returned, the second states when and how to call it. The most load-bearing information (what changed) is front-loaded with zero preamble.

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 does tell the agent which categories of change come back, which is the main thing needed to decide to call it. The gap is that it never says the response carries the next cursor, so an agent must infer where the value for the next `since` comes from.

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 100%, so both parameters are already fully documented, including the 'omit the first time (you get the latest 20)' default and the include_agent default. The description only restates the cursor handoff, which is helpful reinforcement but adds no semantics beyond the 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?

States a specific resource — the set of changes the human made since a cursor — and enumerates the change categories (new tasks, notes and replies, priority changes, unblocks). This clearly separates it from taskhold_list/taskhold_get, which return state rather than a delta. The verb is implicit ('what ... changed') rather than an explicit fetch verb, which keeps it just 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?

Gives three concrete invocation triggers: when you resume, between steps, and before asking the human something. That is unusually actionable guidance for a polling tool. It does not state when *not* to call it or name a sibling alternative, so it stops short of the top score.

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