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

No annotations are provided, so the description carries the behavioral burden. It discloses that results come in order with a cursor, that it returns both published and revised observations, and that it shares an engine with other endpoints. It does not detail edge cases like rate limits or whether cursor offsets are stable, but it provides meaningful behavioral context beyond the raw schema.

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 three sentences with no filler. The first sentence states the purpose and the result ordering/cursor mechanism; the second explains the polling use case; the third ties it to known endpoints. Every sentence earns its place, and the most important information is front-loaded.

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?

For a list/polling tool with no output schema, the description covers what it returns, the ordering, cursor mechanics, and relationship to sibling endpoints. It doesn't explicitly mention that no parameters are required or describe pagination behavior beyond 'bounded server-side' in the schema, but the provided context is largely sufficient for an agent to select and begin using the tool.

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 the schema itself fully documents all five parameters. The description adds a bit of context by explaining the polling model (the 'since' parameter as an offset), but it does not add meaning beyond what the schema descriptions already provide. This meets the baseline of 3.

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 states a clear, specific verb+resource: 'Get every published or revised observation in order with a cursor.' It distinguishes the tool by its cursor/offset polling model and explicitly compares it to related endpoints ('Same engine as /api/events and the vintage archive'). This allows an agent to understand what it does and how it differs from sibling tools like get_revisions or get_vintages.

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 gives explicit guidance on when to use this tool: 'Poll by offset instead of re-pulling series.' This conveys a clear use case compared to alternatives. It does not name a specific sibling tool as the alternative, but the context of 'polling' versus re-pulling makes the intended scenario clear. It lacks explicit 'when not to use' guidance, but for a data-retrieval tool this is adequate.

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