Watch Graph Changes

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

Annotations already declare readOnlyHint=true, so the description adds value by specifying exactly what is observed (mutations and event log entries) and the filtering mechanism. No contradiction with annotations, and the behavior is clear.

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 a single, front-loaded sentence with no fluff. It efficiently conveys the core purpose and scope.

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?

With no output schema and no required params, the description should ideally clarify the return format or whether this is a one-shot or long-polling watch. It doesn't, but it is minimally adequate for a monitoring tool. The lack of return-value info leaves a gap.

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 100%, so all parameters are already documented. The description merely echoes the 'since a timestamp or session' concept, grouping session_id and since_timestamp, but adds no new syntax or formatting details 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 uses a specific verb 'observe' with a clear resource ('state graph mutations and event log entries') and temporal scope ('since a timestamp or session'). It distinguishes itself from siblings like get_event_log by focusing on mutations and the session/timestamp filtering.

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 context for when to use the tool is implied (observing recent changes), but there is no explicit comparison to alternatives like get_event_log or what_changed, nor any exclusion criteria. The guidance is minimal.

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