Cursor: list agents

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable context about ordering ('newest first') and warns that 'Status is not execution state,' which prevents misinterpretation. It does not mention pagination behavior, but annotations cover safety and idempotency.

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 sentences with zero fluff. The main purpose is front-loaded ('List cloud agents, newest first'), and the caveat is a single additional sentence. This is an exemplary concise structure.

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?

The tool has an output schema and annotations that cover safety and idempotency, which reduces the burden. However, the description omits pagination mechanics (limit, cursor) and filtering options (prUrl, includeArchived) beyond what the schema partially provides. Since limit and cursor are undocumented in both schema and description, an agent may not know how to page through results. This is a notable gap for a list endpoint.

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 50%: prUrl and includeArchived have descriptions, but limit and cursor are undocumented in the schema. The description itself adds no parameter information at all, so it fails to compensate for the missing schema coverage. For a tool with four parameters, this leaves half of them ambiguous.

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 clearly states the tool lists cloud agents and specifies ordering ('newest first'). It also adds a clarifying caveat about status not being execution state, which helps differentiate from cursor_get_run. However, it does not explicitly distinguish itself from sibling tools like cursor_get_agent (which retrieves a single agent), so it's not a perfect 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?

The description explicitly tells the agent to use cursor_get_run when execution state is needed, providing a clear when-not condition and pointing to an alternative. It does not discuss other usage contexts or alternatives like cursor_get_agent, but the key exclusion is stated.

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