Stream Active Deploy

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

The description richly discloses behavior beyond the readOnlyHint/openWorldHint annotations: the 2-second polling interval, terminal frame closure, the active-vs-most-recent fallback, the null case for never-deployed apps, and the behavior switch based on the Accept header. This is exemplary transparency for an agent deciding whether and how to invoke the tool.

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 tight sentences with no filler. The first sentence front-loads the primary return contract; the second adds the streaming variant. Every clause carries meaning.

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 there is no output schema, the description covers the frame shape ({ts, deploy}), the nullable deploy case, the streaming mode, interval, and termination — quite complete for an agent deciding to call it. The main gaps are parameter semantics (scored separately) and the lack of any detail about the deploy object's fields, which an agent might need to plan downstream actions.

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 0% — none of the four parameters (workspaceSlug, appSlug, env, region) are explained. Critically, the description does not clarify whether env or region filters which deploy is considered 'active' or 'most recent', leaving a significant ambiguity that the description must compensate for but does not.

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 resource being targeted (the active deploy, or most recent if none is running, or null if never deployed) and the streaming behavior, which distinguishes it well from siblings like listDeploys and streamDeployLogs. The verb 'Returns' and the explicit frame shape make the purpose concrete, though it could more explicitly state that it is for monitoring deploy progress.

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 implicit usage guidance by explaining the one-shot versus streaming mode via the Accept: text/event-stream header, and the 2-second interval/terminal frame behavior. However, it does not explicitly contrast with sibling tools such as listDeploys, streamDeployLogs, or streamAppStatus, so an agent must infer when this tool is the right choice.

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