cursor_request

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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description does not contradict them. The description adds behavioral context not present in the annotations: the sync-deadline deferral behavior, the run-to-completion fallback, the default headless print mode, and the gated acp mode. This gives the agent a clearer model of how the tool executes beyond the safety hints.

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 two dense sentences with no filler, front-loading the core action before transport details. It packs significant information about sync behavior, deferral, default transport, and acp gating without becoming bloated. Some complexity is unavoidable given the tool's scope, but the structure keeps it readable.

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 24-parameter tool with no output schema, the description leaves some gaps: it does not describe what the response looks like, how the deferral should be surfaced, or how the agent should poll the resulting job. The parameter schema is exceptionally rich and compensates for much of the missing context, but the description alone is not fully self-sufficient.

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 individual parameter descriptions are unusually detailed, covering transport-specific rejections, defaults, and flag behavior. The main description adds only a brief summary of which parameters acp accepts, which is largely redundant with the schema. This matches the baseline of 3 for high schema 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 description states a specific action and resource: 'Run a Cursor Agent request synchronously'. It also distinguishes this tool from async variants by explicitly mentioning the sync deadline and auto-deferral to a pollable job. It does not name a sibling like cursor_request_async directly, but the synchronous framing is enough to separate it from the async family of tools.

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 gives useful context about when the tool runs synchronously and when it defers to a pollable job, and it explains the default cli transport versus the gated acp transport. However, it never explicitly tells an agent when to prefer this tool over cursor_request_async or other request tools, nor does it state a clear when-not-to-use condition. The guidance is implied rather than explicit.

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