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

With no annotations, the description carries the full behavioral burden and mostly succeeds. It discloses that results are ordered, deduplicated, structured as diffs (from → to), include change and context blocks, and that low-relevance changes are not filtered. It also describes the lost-response retry behavior. It does not explicitly state read-only/side-effect status or auth/rate-limit expectations, but the acknowledgment-separate flow strongly implies no mutation occurs.

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?

Every sentence earns its place: it front-loads the critical directive, explains when to call, what the output looks like, what filtering behavior exists, and what to do next. There is no filler or repetition.

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 no output schema and no annotations, the description provides enough for an agent to call and consume the tool correctly: response shape, ordering/dedup behavior, next-step acknowledgment, and retry behavior on lost responses. Both parameters are fully documented in the schema, and no required parameters exist.

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%, and the schema already documents `limit` (default/max) and `since` (cursor position semantics). The description reinforces the acknowledgment/cursor relationship but does not add new parameter-level meaning beyond what the schema provides, so the baseline of 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?

The description states a specific operation: it returns every change to watched things since the last acknowledged cursor, ordered and deduplicated. It also distinguishes itself from the follow-up sibling `acknowledge_changes` by clarifying that this call does not acknowledge changes, so an agent cannot confuse the two.

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?

Usage timing is explicit: 'THE FIRST CALL WHEN RESUMING' and 'Call this before continuing any plan you formed in an earlier run.' It also tells the agent to call `acknowledge_changes` afterward. However, it does not explicitly name an alternative tool for filtered or per-subject queries, so there is clear context but no explicit when-not-to-use guidance.

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