query_live_capture_entries

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

With no annotations provided, the description carries the behavioral disclosure burden and does so well: it states the tool does NOT advance the cursor, is safe to call repeatedly, defaults cursor=0 to scan from the beginning, and defines since_seconds as relative to query time. It does not cover every possible behavioral nuance, but the non-mutating, stateless nature is clearly conveyed.

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 longer than average but earns its length by front-loading the recommended usage and providing routing and cursor semantics. The get_traffic_entry_detail pointer appears twice in slightly different forms, which is a minor redundancy. Overall it remains well-structured and readable for the complexity involved.

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 description covers tool selection, cursor safety, and the recent-traffic shortcut, which is enough for basic correct use. However, with 25 parameters, no annotations, and no parameter-level descriptions in the schema, the high-level guidance is not sufficient for an agent to confidently use advanced filters or presets. An output schema exists, but that does not compensate for the underdocumented input semantics.

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%, so the description must compensate; it only explains cursor and since_seconds. The remaining 23 parameters, including preset, scan_limit, max_items, min_priority_score, and the JSON query filters, are left to be inferred from their names and enum values. This is a significant gap for a 25-parameter tool.

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 verb ('Analyze') and resource ('active live capture'), and explicitly frames the tool as the recommended way to inspect live/ongoing traffic. It clearly distinguishes itself from query_recorded_traffic and analyze_recorded_traffic, and positions itself as a summary layer before get_traffic_entry_detail. An agent can confidently tell what this tool is for and how it differs from siblings.

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 explicit when-to-use guidance: prefer this for live/ongoing traffic, use recorded-analysis tools only when the user names a saved .chlsj recording. It also instructs to call this summary path before get_traffic_entry_detail, and recommends since_seconds for 'just now / recent' queries. This is exemplary routing guidance with named alternatives and conditions.

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