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

With no annotations, the description carries full burden. It discloses key behaviors: only watches for NEW events, does not backfill, and pushes notifications. However, it does not mention idempotency, error handling, or authorization needs, leaving some gaps.

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 (two sentences plus filter list) and front-loads the purpose. Every sentence adds information without redundancy. Room for minor improvement in structure (e.g., bullet points for filters).

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 description omits the return value (e.g., watch ID) and error scenarios. Since no output schema is provided, the description should cover what the tool returns. This gap makes it incomplete for an agent to fully understand the tool's behavior.

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?

The description adds value beyond the schema by stating that keyword and entity are case-insensitive substrings, and that at least one filter (keyword or entity) is required despite the schema only requiring destinationType and destinationTarget. It does not elaborate on destination parameters, but schema covers them (80% 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 states the tool creates a saved watch that triggers notifications on new matching events. It uses a specific verb ('Create') and resource ('saved watch'), and distinguishes from sibling watch tools (e.g., alerts_list_watches, alerts_delete_watch).

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 description provides filter requirements (at least one of keyword/entity) and clarifies that backfill never fires. It implicitly guides when to use (for new event notifications) but does not explicitly mention alternatives like alerts_list_watches for viewing existing watches.

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