jobd_events

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

With no annotations, the description carries the full behavioral burden. It reveals that events include skip reasons, cancellations, watchdog kills, etc., and mentions that hook-ingested events may have custom names. It also notes that the broker clamps the limit to 10000. However, it does not mention whether the tool is read-only or has any side effects (likely read-only), nor authentication requirements or rate limits.

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 concise and front-loaded, starting with the core purpose, then immediately contrasting with /jobs, and finally listing filters. Every sentence serves a purpose and there is no fluff. It is well-structured for quick agent parsing.

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 no output schema, the description should ideally describe the return format or structure of events. It does not explain what fields each event contains (e.g., timestamp, type, payload). While the description conveys the nature of events, an agent might need to know the shape of the response to extract relevant information. This gap reduces completeness.

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 100%, so baseline is 3. The description adds value by listing filter options with example formats (e.g., '2h/3d/1w' for since) and enumerating known event types, which is not present in the schema (the schema only defines event as a string). This provides meaningful context beyond the schema.

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 defines the tool as 'the broker's event stream' that explains the 'WHY', not just the 'what'. It distinguishes from sibling tools like jobd_status by stating that jobd_status alone does not explain certain job behaviors, and provides concrete examples of events like dispatch_skip or watchdog_fired.

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?

Explicit usage guidance: 'Use when a job is not doing what you expect and jobd_status alone does not explain it.' This sets clear contextual boundaries. The description also lists available filters, helping the agent understand how to narrow results. No alternative tools are named, but the contrast with jobd_status serves the same purpose.

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