nt_subscribe

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

Without annotations, the description must disclose behavior, and it does cover response format, sample_interval decimation, change_only threshold, and format='summary' aggregation. However, it does not mention side effects (e.g., whether the subscription is one-shot or persistent), rate limits, or cleanup requirements. It provides moderate behavioral insight but leaves significant 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 exceptionally compact, using three short paragraphs to convey purpose, response format, and key parameter behaviors. Every sentence adds value, and the structure front-loads the core idea before diving into parameter specifics. No fluff or redundancy.

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 the tool's complexity (5 params, output schema present), the description covers the core functionality well: sampling under prefixes, duration, decimation, change thresholds, and summary statistics. It does not address error handling, connection prerequisites, or interaction with sibling tools, but the existence of an output schema and related lifecycle tools mitigate the need for those details. A strong, focused description.

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 coverage is 0%, so the description must explain parameters. It effectively details sample_interval (decimation), change_only (threshold), and format (samples vs. summary) with behavioral semantics. Prefixes and duration are left implicit, but their meaning is evident from the schema and context. This strongly compensates for the schema's lack of descriptions.

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 uses a specific verb 'Sample' with a clear resource (value updates under prefixes) and a time boundary (duration). The response format is also given, which helps distinguish it from siblings like nt_subscribe_offline. However, it could be more explicit about the subscription mechanism and does not name alternatives, so a 4 is warranted.

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?

No guidance is provided on when to use this tool versus siblings like nt_subscribe_offline, nt_start_subscription, or nt_poll_subscription. The description focuses solely on parameter effects and output, omitting use cases, prerequisites (e.g., an active nt_connect), or when not to use it. This leaves the agent without decision criteria for tool selection.

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