events_sample

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

With no annotations provided, the description carries the full burden, and it reveals important behavioral traits: the event count is capped at 500, windows over ~24h are rejected, and it is a narrow-window sample rather than a comprehensive query. It does not describe error behavior or ordering, but for a read-only sampling tool the key constraints are surfaced clearly.

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?

Three terse sentences, each carrying a distinct piece of information: what it is, its hard limits, and when to use it. The text is front-loaded with the essential purpose and avoids explaining what the schema already covers. Every clause earns its place.

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 tool has 8 parameters, no output schema, no annotations, and only 13% schema description coverage. The description does not clarify the required 'prefix' semantics, any of the optional filter parameters, or the structure of the returned raw events. While the usage guidance is strong, an agent is left to guess important call details, so the overall description is not complete enough.

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 only 13% (just start), and the description only adds meaning for the window and cap, implicitly linking start/end/limit. It says nothing about the required 'prefix' parameter or the optional filters (peer_asn, origin_as, event_type, collector_id), leaving the agent without semantic guidance for the majority of parameters. The description fails to compensate for the low schema coverage.

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 identifies the tool as providing 'Bounded raw events for a NARROW window' and frames it as a 'last resort' after other tools, which makes its resource and scope explicit. It distinguishes itself from siblings by positioning itself against timeline, reachability, and origin_history, which tells an agent what this tool is not for.

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 explicitly states when to use this tool: 'Use only after timeline/reachability/origin_history have localised what you need to see at the message level.' It names the alternatives and gives concrete constraints (capp at 500 events, rejects windows over ~24h) that help an agent decide if this tool fits the task. This is strong, actionable guidance.

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