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

With no annotations available, the description carries the behavioral disclosure burden and does well: it discloses the payment requirement ($0.05 or $0.02), the HTTP 402 on unpaid requests, the need for a valid X-PAYMENT header, and the fact that the same URL switches from payment gate to JSON response. It does not describe response shape or chunk size, but the core behavior of this paid endpoint is transparent enough.

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 compact and front-loads the endpoint and payment terms. It wastes few words, though the phrase 'Not a new SKU.' is cryptic and the first sentence mixes URL, pricing, and payment address into a dense statement. Still, every clause contributes relevant information.

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 tool with no output schema and no annotations, the description thoughtfully covers payment, errors, and access modes, but it leaves gaps: it does not explain what the returned JSON contains, how to obtain a valid X-PAYMENT, or what defines a 'chunk' in terms of size or boundaries. An agent could probably call it, but not with full confidence about the response format or payment preconditions.

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 parameter semantics are already well-documented in the schema. The description adds high-level mapping like ?id= and ?before, but it does not add meaningful detail beyond the schema descriptions for page, before, id, or x_payment. Baseline 3 applies because the schema already does the heavy lifting.

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 identifies the resource as 'EPA Superfund Record of Decision text' and distinguishes retrieval modes: one official text via ?id, the newest chunk via plain GET, and older chunks via ?before. While the first sentence focuses on payment and URL rather than a clear verb like 'fetch', the overall intent is understandable and separable from sibling tools by the named resource.

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 context for when to use each request style ('plain GET' for newest chunk, '?before' for older chunk, '?id=' for one official text), but it never addresses when to choose this tool instead of a sibling tool or what distinguishes it from related endpoints like get-page or ticks. The usage context is implied, not explicitly routed against alternatives.

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