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

Annotations already mark the operation as read-only and non-destructive. The description adds meaningful behavioral context beyond that: tombstones are included, pagination terminates via has_more, the 'latest' mode skips historical events, and callers must respect poll_after_seconds. This is useful, though it does not cover response entities or error conditions.

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?

Three short sentences, each carrying distinct information: what is polled, how to paginate, and how to handle the 'latest' mode. There is no filler or repetition; the most important framing is front-loaded.

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, the description reasonably covers pagination via has_more and the history-skipping behavior, which are the key operational details. It is slightly incomplete in not describing what a change/tombstone event looks like or when a caller should prefer this over get_sync_changes, but it is sufficient for basic correct invocation.

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 operational semantics for the cursor parameter—'copy cursor until has_more=false' and 'latest skips history'—which clarifies how the existing cursor/limit parameters are meant to be used together. This goes slightly beyond the schema without redundancy.

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 that the tool polls 'bounded metadata events, including tombstones,' which clearly identifies it as a change-tracking/polling operation for members. It uses a specific verb and resource, though it does not explicitly differentiate itself from the very similar sibling get_sync_changes.

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 clear procedural guidance: copy the cursor until has_more=false, use 'latest' to skip history, read changed resources, and honor poll_after_seconds. This gives the agent concrete usage context, but it does not explicitly state when to choose this tool over alternatives like get_sync_changes or list_knowledge_changes.

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