nt_subscribe_offline

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

There are no annotations. The description is solely burdened with behavioral traits. It mentions that 'format=summary' returns min/max/mean/last per topic, but it doesn't say what happens for the subscription until it stops, what data is returned, or about invalid parameters/permissions/errors. It does not contradict the annotations, as they are absent.

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?

One dense sentence with inline code; efficient in space, but the inline sentence is a bit hard to parse. Not too long.

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 output schema is provided, so the return shape need not be spelled out; yet the description doesn't give information about the'last_seconds' positions and the meaning of 'limit'/'start'/'end'. The live subscription vs offline context is implicit, not explicit.

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 has many optional parameters (start, end, limit, output_dir, recording_id) and the descriptions are not provided. The description is limited to prefixes, but the interplay of the last few params is unclear. The described params: prefixes, last_seconds, sample_interval, format. Mapping between several optional params is not useful.

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: 'return events for every topic under prefixes from a recording.' This is clear and distinguishes this tool as an offline subscription tool. It doesn't name sibling tools, but the offline/recording context separates it enough.

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 context of use is clear: this is for a recording rather than a live connection. It does not explicitly explain when to choose this over nt_subscribe or nt_get, but uses the word 'from a recording' and the 'offline' in the name.

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