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

No annotations are present, so the description carries the full behavioral disclosure burden. It explicitly discloses payment requirements, the HTTP 402 response when unpaid, the JSON response after a valid X-PAYMENT, and the 304/recordCount 0 behavior for empty since results. This is candid and detailed, though it does not address any potential side effects, which are presumably none for a read-only GET.

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 a single dense paragraph that packs endpoint, pricing, query modes, and error behavior into a few sentences. While the semicolon-heavy structure is a bit run-on, every clause provides necessary information and there is no extraneous filler.

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 tool has five optional parameters, no output schema, and no annotations, which puts a premium on the description to explain both invocation and response. It thoroughly covers invocation and payment but only vaguely mentions 'returns JSON' without describing the response shape or fields. An agent calling this tool might not know what to do with the JSON without further documentation.

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 input schema already covers 100% of parameters with detailed descriptions, including pricing and semantics, so the baseline is 3. The main description adds a conceptual framing (e.g., 'plain GET' is the newest chunk, id is one official text) but mostly paraphrases what the schema already provides, so it does not substantially raise the score.

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 names the specific resource (NMB representation determination text) and the operation (HTTP GET), which clearly distinguishes this tool from its many sibling tools covering other agencies. The pricing and endpoint details reinforce the purpose even though they are presented in a dense style.

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 provides detailed guidance on which query parameter to use for different retrieval needs (specific id, newest chunk, older chunk, watermark filter) and their associated costs. However, it does not explicitly compare this tool to sibling tools or state conditions when one should avoid this tool; the differentiation from siblings is only implicit through the unique resource name.

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