get_changes

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

With no annotations provided, the description carries the full behavioral burden. It usefully discloses that changes include the user's own edits and that a last event number is returned, but it omits ordering, whether all change types are included, and confirmation that this is a read-only operation.

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 a single compact sentence that front-loads the scope and cursor behavior. The phrasing around 'and `last`' is slightly fragmented, but there is no wasted text.

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 one-parameter read tool with no output schema, the description covers the key cursor semantics and parameter meaning. It still leaves the exact shape of the returned changes list and the choice versus get_history implicit, which is a meaningful gap for agent selection.

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%, so the description must explain the sole parameter. It does so by defining since as an event number, noting that 0 means all kept, and connecting it to the returned last value for the next call. It could be clearer about inclusivity and the source of event numbers, so it is not a 5.

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 makes clear that this retrieves changes after an event number and returns a last cursor, so the action and resource are understandable. However, it does not explicitly name a verb or differentiate itself from the sibling get_history tool, so it falls 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?

It implies an incremental polling usage pattern: use since=0 for all kept changes and pass the returned last value next time. It does not state when to choose get_changes over get_history or any exclusions, leaving the comparison to inference.

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