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

Beyond the readOnlyHint, idempotentHint, and destructiveHint annotations, the description discloses the unusual billing behavior, the idempotency nuance ('asking the same question again while the set has not grown is free'), authentication options, and the equivalent HTTP route. This gives the agent substantial operational context beyond the structured annotations.

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 first sentence is excellent and front-loaded. However, the billing condition is stated redundantly: '$0.002 ONLY when we filter at least one item out...' is followed later by 'Costs $0.002 USDC per call via x402 on Base, and ONLY when filtered_count >= 1...' The paragraph is information-dense but could be tightened.

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 three-parameter tool with no output schema, the description covers invocation semantics, authentication, cost behavior, and what the result means. It does not specify the exact response shape, but it does describe the outcome well enough for an agent to select and interpret the call correctly.

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 schema already documents all three parameters at 100% coverage, so the baseline is 3. The description adds value by clarifying that agent_key is a fallback only when headers cannot be set, that the header is preferred, and that items are capped at 100 strings. These details go beyond the schema's examples.

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: 'Given a batch of items, return only the ones not already in the set.' This clearly defines a filter operation and distinguishes it from sibling tools like seen_add, which would add items to the set rather than check them.

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 strongly implies when to use the tool: when you need to determine which items from a batch still need processing. It adds practical conditions like the 100-item limit and the free-call behavior when nothing is new. It does not explicitly mention seen_add as the alternative for recording seen items, so it stops short of a full when-to-use vs alternative statement.

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