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

Annotations already mark this read-only and idempotent, and the description enriches that with billing behavior, free re-reads, the no-watermark case, authentication requirements, and the exact cost trigger. It also confirms the route. This goes well beyond annotations without contradicting them.

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 core purpose is front-loaded, but the billing explanation is repetitive: the $0.002 condition is stated multiple times in slightly different forms. The description is useful but would be tighter if the cost rules were consolidated into one sentence.

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 covers the main call context, empty-watermark behavior, auth, HTTP route, and billing. With no output schema, it does not spell out the exact response shape, but it clearly implies the returned position and the no-watermark notification. This is complete enough for a simple read tool backed by strong annotations.

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 coverage is 100%, so the baseline is 3. The description does mention passing agent_key when headers cannot be set, but this largely duplicates the schema's own guidance. No significant new parameter-level semantics are added beyond what the schema already provides.

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 opens with a specific verb and resource: 'Fetch the position you last recorded for a stream.' It clearly distinguishes this from watermark_set (writing a watermark) and other state tools by explaining the upstream/new-items use case. The title is colloquial, but the description removes ambiguity.

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 clear context for when to use the tool: before asking an upstream for only what has changed since the last recorded position. It does not explicitly name alternative tools or exclusion conditions, but the usage intent is strong and paired with watermark_set as an obvious sibling.

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