listObservations

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

No annotations are provided, so the description carries the full burden. It discloses pagination method and that results include metrics, costs, and latency. However, it does not mention ordering, rate limits, or that the tool is read-only, leaving gaps in behavioral context.

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 two sentences long, front-loads the core action and resource, and contains no extraneous information. Every word serves a purpose.

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 the rich input schema and absence of annotations and output schema, the description adequately covers purpose and pagination but omits details like default ordering or behavior of time-range filters. It is sufficient but not exhaustive.

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?

All 10 parameters are fully described in the input schema (100% coverage). The description adds no new meaning about parameters beyond what schema already provides, so the baseline score of 3 is appropriate.

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 action (list), resource (observations), and specifies the types included (generations, spans, events). It also mentions cursor-based pagination and included data (usage metrics, costs, latency), effectively distinguishing from sibling tools like getObservation or listTraces.

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 implies usage for listing observations with pagination but provides no explicit guidance on when to use this tool versus alternatives (e.g., getObservation for a single item). There are no when-not-to-use notes or comparisons to siblings.

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