obs_watch

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

Describes behavior: returns recent events, can wait, excludes audio meters. Since no annotations, this is sufficient. No side effects mentioned but implied read-only.

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?

Well-structured, not overly verbose, covers all necessary points without redundancy.

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?

Covers purpose, usage, what it returns, what it excludes; sufficient for common use cases. Lacks details on error handling but not critical.

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 already describes parameters; description reinforces by explaining forMs as waiting, limit as count, and types as filtering with examples. Adds context to 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?

Clearly states it retrieves recent event stream events, distinguishes from polling, and gives examples of event types.

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?

Explicitly advises when to use (for historical events vs current state) and mentions optional waiting for upcoming events, and contrasts with obs_who_is_talking.

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