Cursor: recent run activity

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses the bounded read behavior, the resume-vs-replay semantics of lastEventId, and the fact that status is intentionally not included and the run is not canceled. These are meaningful behavioral traits not encoded in 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?

Three compact sentences: the main action is front-loaded, then continuation behavior, then the important non-behaviors. There is no filler, repetition of annotations, or redundant parameter detail.

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 read-only tail-style tool with an output schema and strong annotations, the description covers the essential contract: what is read, how to resume, and what it does not do. The only minor gap is not explicitly tying durationMs to the 'bounded' wording, but the schema default and range make the connection recoverable.

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?

The description explains the most subtle parameter, lastEventId, by saying it resumes the stream and that omitting it causes a replay from the beginning. The 'bounded' qualifier makes durationMs inferable alongside its schema default, and agentId/runId are self-evident identifiers, which partially compensates for the 0% schema description coverage.

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 opening sentence states a specific verb (Read), resource (run activity), and scope (bounded excerpt), so the purpose is immediately clear. It distinguishes itself from get/list/wait siblings by noting status is checked separately and that it does not cancel the run, though it does not name the sibling explicitly.

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 gives direct usage guidance: pass lastEventId back to resume, otherwise Cursor replays from the beginning. It also sets clear exclusions by saying status is checked separately and the tool does not cancel the run, though it stops short of naming the alternative tools.

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