nt_start_subscription

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

The description mentions the response fields and the need to poll and stop, which gives a sense of the tool's behavior. But with no annotations, it does not disclose potential errors, side effects, or resource implications, leaving important transparency gaps.

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 concise and well-structured. It states the purpose, gives the response format, and mentions the follow-up tools in a clear, direct manner without superfluous details.

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?

While the overall flow is outlined, the lack of parameter explanations and error handling makes it incomplete. The tool's complexity is moderate, but the description fails to provide essential context for confident usage.

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 schema provides three parameters (prefixes, buffer_size, subscription_id) but the description offers no explanation for any of them. Since schema coverage is 0% and the description does not compensate, the agent has no idea what these parameters mean or how to use them.

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's function: 'Open a persistent subscription and start collecting samples.' It explicitly mentions the response structure and the complementary tools for polling and stopping, which distinguishes it from sibling tools like nt_subscribe or nt_poll_subscription.

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 provides a clear workflow: start, then poll, then stop. This implies when to use the tool (as the initial step in a persistent subscription flow). However, it does not explicitly contrast with other subscription methods (e.g., nt_subscribe might be one-shot), so it falls short of being fully explicit.

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