peek_live_capture

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

With no annotations, the description carries the full burden and it does well: it explicitly states the call does not consume messages, is safe to call repeatedly, and returns only compact summaries. That covers the most important behavioral traits an agent needs before invoking it.

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 front-loaded with the core behavior and every sentence adds value. It loses a point because the 'does not consume' point is made twice: 'does not consume the current increment' and 'does not consume items'.

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?

For a simple peek tool with an output schema, the description covers the core behavior well, but it is not fully complete: it does not explain the meaning of capture_id, limit, or cursor beyond the cursor hint, and it does not state needed prerequisites such as an active capture. These gaps are moderate given the low parameter-level documentation in the schema.

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 the parameters, but it mostly does not. The only partial light shed is on cursor through the wording 'does not advance the current cursor'; capture_id, limit, and full cursor semantics remain unexplained.

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 verb and resource: it previews incremental traffic but does not advance the cursor. It also notes the return type is compact entry summaries, which helps distinguish it from read_live_capture and query_live_capture_entries. The final sentence explicitly routes structured uses to a sibling, reducing ambiguity.

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 directly says to use query_live_capture_entries for structured filtering and analysis, which is a useful when-to-use alternative. The 'does not consume' wording implicitly tells the agent to use this tool when it wants a side-effect-free preview, but it does not explicitly mention when to choose read_live_capture instead, so the when-not boundary is slightly incomplete.

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