User activity

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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description is fully consistent with a safe read/poll operation. Beyond the annotations it discloses the incremental cursor semantics (lastSeq round-trip), the concrete payload shape, and a safety constraint about not clobbering concurrent user edits — real behavioral context the agent could not infer from the structured fields.

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, front-loaded with what is returned followed by how to call it safely; every clause carries information. The event-type enumeration is long but each item is genuinely useful given there is no output schema.

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 must describe return values, and it does so item by item including lastSeq and per-edit history titles/ids. Combined with the polling guidance and the pre-mutation safety note, an agent has everything needed to call it correctly.

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 nonetheless adds the idiomatic usage of the single parameter — feeding back the lastSeq from the prior call to get a delta — which the schema alone does not convey. It stops short of discussing the default or edge cases, so it is an increment rather than a complete treatment.

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 (return) plus the exact resource (user activity events since a sequence number) and enumerates the event categories returned: selections, edits with history title and ids, Alt+Space prompts, saves, navigations, and lastSeq. This is clearly distinguishable from siblings like wait_for_user_prompt or canvas_status.

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 an explicit invocation pattern — 'Pass since=<lastSeq of your previous call> to get only new events' — and an explicit pre-mutation workflow naming the alternative tools to re-read (get_canvas_skeleton, inspect_element) with the reason (avoid overwriting user edits). Both when-to-use and the recommended sequencing are spelled out.

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