get_capture_metadata

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It discloses that the result comes primarily from Capinfos, implying a standard tool output, and notes that it does not return packet dissections, which is a key behavioral trait. It also implies that metadata is returned 'when available', setting expectations for partial results. However, it does not mention any side effects (likely none since read-only), or the exact format of the returns, but given the tool is read-only and the output schema exists, this is sufficient.

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 well-structured with a clear main sentence, a 'Use this for' clause that lists use cases, a note on limitations, and then structured Args and Returns sections. It is front-loaded with the main purpose. The length is appropriate for the complexity. Minor redundancy exists ('Returns:' section repeats some information from the use-list), but overall it is concise and organized.

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 has a single parameter, a complex use case (metadata inspection), and an output schema (which likely describes the structure of returned metadata), the description is mostly complete. It covers the primary use cases, the limitation, and parameter semantics. The absence of mention of error conditions (e.g., if capture_id is not found) is a minor gap, but the output schema and the tool's likely behavior as an inspect operation mitigate this. Overall, it is sufficient for an agent to use effectively.

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 compensate. The description explains that 'capture_id' is the ID of a currently loaded capture, which adds critical context about the parameter's meaning and prerequisite (must be loaded). This goes beyond the schema's bare 'string' type. The description also explains what the parameter is used for (identifying which capture to inspect). This is strong compensation for the lack of schema documentation.

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 inspects PCAP/PCAPNG container and capture-interface metadata, listing specific aspects like file format, encapsulation, snap length, timestamp precision, capture origin, comments, time range, and per-interface information. It also explicitly notes that it does not return packet dissections, distinguishing it from dissection tools. This is a specific verb-resource combination that effectively differentiates it from siblings like dissect_packet or get_packet_by_number.

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 implies usage for metadata-related inquiries about a capture (e.g., file format, timing, interfaces) and states that it does not do packet dissections, which helps with when-not-to-use. It does not explicitly name alternative tools for when packet dissections are needed, but the exclusion is clear. Given the context, this is adequate but could be improved by explicitly pointing to dissect_packet for packet-level analysis.

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